© 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. 239311
    Prev
    Next
    INDEX
    Explanations

    shorter, smaller, under, drop

    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
     തന്നെയാണ്
    0.52
     meerdere
    0.49
     │
    0.46
     ഒന്ന
    0.45
    itsyn
    0.44
     wówczas
    0.42
     CURLE
    0.42
     đội
    0.42
    ,=
    0.42
    getAvg
    0.41
    POSITIVE LOGITS
     explorations
    0.47
    est
    0.46
    请求
    0.45
    xious
    0.45
    invasion
    0.44
     القدم
    0.43
     الحض
    0.43
    ad
    0.43
    requests
    0.43
    jobs
    0.42
    Activations Density 0.007%

    No Known Activations