© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38122
    Prev
    Next
    INDEX
    Explanations

    words starting with a sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sprintf
    0.41
    prompt
    0.41
     Goodyear
    0.39
    尔
    0.39
     pneus
    0.38
     lambda
    0.38
     NIST
    0.37
     upstate
    0.37
    ಹಿತ
    0.37
    义务
    0.37
    POSITIVE LOGITS
     спе
    0.44
    🏦
    0.43
    ции
    0.42
     за
    0.42
     विजेता
    0.42
    мов
    0.41
     ferocious
    0.41
     venced
    0.41
     favoured
    0.41
     ракет
    0.41
    Activations Density 0.006%

    No Known Activations