© 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. 1172
    Prev
    Next
    INDEX
    Explanations

    starting sequences from lists or special cases

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

    simple visualizations, Circle, past

    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
     together
    0.49
     RO
    0.48
    কে
    0.46
     Lega
    0.46
     inplace
    0.46
     chiq
    0.46
     R
    0.45
     from
    0.45
    ;
    0.45
     EU
    0.45
    POSITIVE LOGITS
    اقة
    0.56
    دع
    0.49
    ném
    0.48
    ليف
    0.48
    жі
    0.47
    کنش
    0.47
    ర్‌లో
    0.47
    لوث
    0.47
     liegen
    0.46
    افه
    0.46
    Activations Density 0.000%

    No Known Activations