© 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. 160634
    Prev
    Next
    INDEX
    Explanations

    specific words following punctuation or special characters

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

    vector space, query, GPT, Matrix

    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
     "#
    0.53
    {"
    0.48
     "
    0.43
    Qualification
    0.43
     забе
    0.42
     Qualification
    0.42
     +"
    0.41
     본격
    0.41
     "{
    0.40
     Governance
    0.40
    POSITIVE LOGITS
     presentazione
    0.56
     prezent
    0.54
     তাঁহার
    0.52
     apparaît
    0.52
    ੴ
    0.49
     digitale
    0.46
     poter
    0.46
     vele
    0.45
     velič
    0.45
     vect
    0.45
    Activations Density 0.000%

    No Known Activations