© 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. 136279
    Prev
    Next
    INDEX
    Explanations

    discovered within context

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

    "and" followed by CO or historically

    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
     acteur
    0.51
    sprech
    0.48
     деклара
    0.46
    <unused1911>
    0.46
     मैथमेट
    0.45
    <unused199>
    0.45
    <unused385>
    0.45
    蛐
    0.45
    ల్యే
    0.44
    膯
    0.44
    POSITIVE LOGITS
    INN
    0.51
     στις
    0.47
     ang
    0.45
    ndvi
    0.45
    ur
    0.45
     कर
    0.44
    indigo
    0.43
    ang
    0.43
     horsepower
    0.43
     shutterstock
    0.43
    Activations Density 0.000%

    No Known Activations