© 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. 168802
    Prev
    Next
    INDEX
    Explanations

    Mexico, files, Senators

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

    categories and specific items

    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
    <td>
    0.49
    вчи
    0.46
    Platform
    0.46
    Finance
    0.46
    *}\
    0.45
    mang
    0.43
    venture
    0.42
    COVERY
    0.42
    㴦
    0.42
    str
    0.41
    POSITIVE LOGITS
     costumes
    0.50
     predictions
    0.49
     regimens
    0.49
     droughts
    0.47
     garages
    0.46
     emojis
    0.46
     celu
    0.46
     norms
    0.45
     closets
    0.45
     casualties
    0.44
    Activations Density 0.001%

    No Known Activations