© 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. 64556
    Prev
    Next
    INDEX
    Explanations

    usernames and handles

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

    chat identifiers like names

    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
    rootScope
    0.44
    ")->
    0.42
    getName
    0.42
    setObjectName
    0.42
    httpRequest
    0.42
    indelijk
    0.41
    apadani
    0.41
     សូម
    0.40
    ">{
    0.40
    glfw
    0.39
    POSITIVE LOGITS
     referido
    0.44
     sugest
    0.44
     &/
    0.44
     dicho
    0.43
     esses
    0.43
    sulph
    0.42
     dicta
    0.42
    ｽ
    0.42
     gave
    0.42
    さんの
    0.42
    Activations Density 0.044%

    No Known Activations