© 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. 97609
    Prev
    Next
    INDEX
    Explanations

    lots of

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

    tailor and enhance existing

    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
     apparaissent
    0.47
    ங்களையும்
    0.47
    이지만
    0.46
     ď
    0.46
     urm
    0.46
     שנ
    0.46
     chcesz
    0.46
    同士
    0.45
     】,
    0.44
     били
    0.44
    POSITIVE LOGITS
    government
    0.47
    owners
    0.43
    indows
    0.43
     representantes
    0.43
     países
    0.42
    WAL
    0.42
    favor
    0.42
    ا
    0.42
    өрү
    0.41
    favorite
    0.41
    Activations Density 0.000%

    No Known Activations