© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13159
    Prev
    Next
    INDEX
    Explanations

    DIFFERENT

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

    The neuron sharply activates on semantically rich content words (nouns, verbs, adjectives) rather than on function or stop words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     &/
    1.06
     Jika
    1.02
     있으며
    1.01
     (
    0.98
     лише
    0.98
     אך
    0.96
     &
    0.95
     หาก
    0.93
     jika
    0.93
    மின்றி
    0.93
    POSITIVE LOGITS
     ähm
    1.57
     그다음에
    1.42
     굉장히
    1.31
    っていう
    1.30
     uh
    1.27
     ờ
    1.26
     gonna
    1.22
     немно
    1.20
    比如说
    1.20
     äh
    1.19
    Activations Density 1.087%

    No Known Activations