© 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. 10265
    Prev
    Next
    INDEX
    Explanations

    opening parenthesis

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

    The neuron responds strongly to any token containing the letter sequence “str,” i.e. parts of words like straddles, Strachan, Stratmann, Strangely, etc.

    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_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
     Abelian
    0.57
    [:-
    0.55
     Integer
    0.54
    )*
    0.53
    /*.
    0.53
     Examine
    0.53
    Align
    0.53
     gegen
    0.52
    Integer
    0.52
     [-
    0.52
    POSITIVE LOGITS
    攬
    0.58
    孖
    0.57
    合作
    0.56
    鈔
    0.56
    ({
    0.55
     fortes
    0.55
     zarządz
    0.55
     HUGH
    0.55
     തീ
    0.54
    ন্ত
    0.54
    Activations Density 0.010%

    No Known Activations