© 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. 212232
    Prev
    Next
    INDEX
    Explanations

    product codes and specifications

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

    describing what it does

    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
     Державний
    0.48
     först
    0.46
     scrutiny
    0.46
     disobedience
    0.45
    秩序
    0.45
     intrig
    0.45
     verstehen
    0.44
    眺
    0.44
     ছাড়াই
    0.44
     Durchschnitt
    0.44
    POSITIVE LOGITS
    local
    0.53
    key
    0.52
     key
    0.50
    icon
    0.49
    scale
    0.49
    to
    0.48
    at
    0.47
    AR
    0.46
    nG
    0.46
    ing
    0.46
    Activations Density 0.000%

    No Known Activations