© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139791
    Prev
    Next
    INDEX
    Explanations

    rpm and specifications

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

    earn before payout

    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
    IfExists
    0.49
    weak
    0.46
    room
    0.45
    ().
    0.44
    ipse
    0.44
    :
    0.44
    imon
    0.43
    Formatting
    0.43
    NonNull
    0.42
    ClientID
    0.42
    POSITIVE LOGITS
     orientado
    0.52
     bút
    0.49
    ಗ
    0.49
     ரே
    0.48
     සො
    0.46
     ગાં
    0.45
    잇
    0.45
    ឿ
    0.45
    を楽しむ
    0.45
    лід
    0.44
    Activations Density 0.000%

    No Known Activations