© 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. 224868
    Prev
    Next
    INDEX
    Explanations

    share information

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

    conditions and limitations

    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
    $',
    0.58
    を開
    0.54
    $'
    0.51
    팡
    0.47
     افتتاح
    0.47
     Negotiation
    0.46
     mở
    0.46
    𝓌
    0.46
    之后
    0.46
    ocument
    0.45
    POSITIVE LOGITS
     ancillary
    0.50
     assistive
    0.48
     simplistic
    0.48
    aver
    0.47
     queued
    0.46
     seamless
    0.46
     casein
    0.45
     ANSI
    0.44
     vanqu
    0.44
     protein
    0.44
    Activations Density 0.001%

    No Known Activations