© 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. 156338
    Prev
    Next
    INDEX
    Explanations

    lower the quota

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

    creating distractions

    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
     disseminate
    0.45
     decoder
    0.44
    乒
    0.44
     مشینیں
    0.42
     survivor
    0.42
    ásticos
    0.42
     мульти
    0.42
     soupe
    0.42
     latitude
    0.41
    快樂
    0.41
    POSITIVE LOGITS
     પ
    0.53
    Poz
    0.53
    Kenya
    0.52
    Sax
    0.51
    as
    0.50
    தல்
    0.50
    窅
    0.49
    श्व
    0.49
    Moon
    0.49
    Cel
    0.48
    Activations Density 0.000%

    No Known Activations