© 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. 237613
    Prev
    Next
    INDEX
    Explanations

    picture States

    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
    不错
    0.52
    ก
    0.51
    є
    0.49
     punct
    0.49
    ้
    0.47
    קט
    0.46
    ித்த
    0.42
    ellan
    0.42
    ת
    0.42
    τητα
    0.41
    POSITIVE LOGITS
     jų
    0.51
    他們的
    0.51
     ihre
    0.45
     يؤ
    0.44
     hysterical
    0.44
     ಅವರ
    0.43
     Intens
    0.43
    รือ
    0.43
    вня
    0.43
     lentes
    0.43
    Activations Density 0.001%

    No Known Activations