© 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. 133778
    Prev
    Next
    INDEX
    Explanations

    links and HTML tags

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

    html tags

    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
     as
    0.60
     아
    0.60
    ات
    0.57
    ة
    0.57
    어
    0.57
    ام
    0.57
    та
    0.55
     두
    0.54
     니
    0.53
    ，
    0.53
    POSITIVE LOGITS
    i
    0.61
    giver
    0.56
    seen
    0.55
    d
    0.55
    venues
    0.54
    ileen
    0.54
    rer
    0.54
    cha
    0.52
    io
    0.52
    ivo
    0.51
    Activations Density 0.000%

    No Known Activations