© 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. 159244
    Prev
    Next
    INDEX
    Explanations

    consulting, application, effort, party

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

    STAR method or specific criteria

    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
     personalization
    0.52
     pollutant
    0.48
    撳
    0.47
     licenses
    0.47
     marketer
    0.46
     legalization
    0.46
     Personalized
    0.46
    ಡುಗೆ
    0.46
     Licenses
    0.45
    грама
    0.43
    POSITIVE LOGITS
    al
    0.54
    eid
    0.53
    cosec
    0.49
    ül
    0.48
    kip
    0.48
     ofer
    0.48
    𝒍
    0.48
    alı
    0.48
    aporte
    0.48
    itl
    0.47
    Activations Density 0.001%

    No Known Activations