© 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. 243941
    Prev
    Next
    INDEX
    Explanations

    meeting and boiling

    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
    コンピュータ
    0.45
    ுடன்
    0.44
    '
    0.44
    Secure
    0.43
     Manage
    0.43
    Web
    0.42
    Colleg
    0.42
     Facilit
    0.41
     Identify
    0.41
    HV
    0.40
    POSITIVE LOGITS
    bson
    0.58
    但他
    0.44
     absolutamente
    0.43
    <unused345>
    0.42
    ív
    0.42
    <unused99>
    0.42
    ស្ថ
    0.41
    不下
    0.41
     αλλά
    0.41
     Âu
    0.41
    Activations Density 0.000%

    No Known Activations