© 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. 34228
    Prev
    Next
    INDEX
    Explanations

    academic record varies

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

    foreign words or specific names

    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
    phyll
    0.53
    o
    0.53
    lle
    0.52
    k
    0.52
    卡
    0.52
    ose
    0.51
    em
    0.49
    ere
    0.49
    sse
    0.49
    in
    0.48
    POSITIVE LOGITS
    闫
    0.55
     Schwier
    0.52
    Stadt
    0.50
    日本語
    0.49
    BUGFS
    0.48
    ஸல்
    0.48
     பாஜக
    0.47
    読む
    0.47
     nier
    0.47
     GitHub
    0.47
    Activations Density 0.000%

    No Known Activations