© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23778
    Prev
    Next
    INDEX
    Explanations

    public followed by programming types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     συγκ
    0.45
    眦
    0.44
     centrally
    0.41
     پ
    0.41
    ʘ
    0.38
    ⓜ
    0.38
     राज
    0.38
    见过
    0.38
    ⌐
    0.38
    都是
    0.38
    POSITIVE LOGITS
     этой
    0.55
     этого
    0.52
     этом
    0.52
     acest
    0.49
     dieser
    0.49
     этому
    0.48
     tejto
    0.47
     denna
    0.47
     této
    0.46
     цього
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.