© 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. 122778
    Prev
    Next
    INDEX
    Explanations

    shares purchased

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

    rights, performance, interest

    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
    izens
    0.45
    onnen
    0.45
     앱
    0.45
    uč
    0.44
    igned
    0.44
    Been
    0.43
    챌
    0.43
    ěn
    0.43
    ok
    0.43
    conn
    0.42
    POSITIVE LOGITS
     derechos
    0.59
     Derechos
    0.55
     incor
    0.49
    ATTRIBUTE
    0.47
     schist
    0.47
     direitos
    0.46
     uninsured
    0.46
     tetanus
    0.46
     Exchequer
    0.46
     parasites
    0.46
    Activations Density 0.002%

    No Known Activations