© 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. 9542
    Prev
    Next
    INDEX
    Explanations

    ala:

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

    counting or ranking

    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
     $
    0.54
     &
    0.54
    &
    0.53
    new
    0.52
    c
    0.52
     new
    0.50
    Ex
    0.50
    S
    0.50
    C
    0.50
    ,
    0.49
    POSITIVE LOGITS
     harming
    0.54
     músculos
    0.52
     ব্যথা
    0.52
    ochlor
    0.50
    PAssignment
    0.50
     угла
    0.49
     âmbito
    0.49
     instituted
    0.48
    ollip
    0.47
    calright
    0.47
    Activations Density 0.000%

    No Known Activations