© 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. 65069
    Prev
    Next
    INDEX
    Explanations

    languages or code-switching

    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
    unjukkan
    0.49
    図柄
    0.45
    क्रीम
    0.45
    胛
    0.45
     Variability
    0.43
     pulsations
    0.42
    我们需要
    0.42
    鸰
    0.41
    gdock
    0.41
     Risk
    0.41
    POSITIVE LOGITS
     ويك
    0.42
    یاط
    0.41
     تھا
    0.39
     そして
    0.39
    抄
    0.39
    WhiteSpace
    0.38
    spaces
    0.38
     wahr
    0.38
    يب
    0.38
     لکھ
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.