© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7562
    Prev
    Next
    INDEX
    Explanations

    hashtags

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects social‐media style hashtags (the “#” symbol and the words immediately following it).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    hashtags and social media tags.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    social media and blog metadata like hashtags, usernames, and comma‑separated keyword/tag lists.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (%)
    0.74
    -/
    0.69
     compds
    0.68
    -,
    0.68
     \&
    0.65
     (.
    0.65
     (-)
    0.64
     (\%)
    0.64
    -.
    0.63
    (-)
    0.63
    POSITIVE LOGITS
     #
    2.02
    #
    1.51
    스타그램
    1.45
    ,#
    1.42
     ##
    1.23
     #(
    1.23
    ofinstagram
    1.22
     "#
    1.20
     hashtag
    1.19
    ;#
    1.17
    Activations Density 0.192%

    No Known Activations