© 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. 179260
    Prev
    Next
    INDEX
    Explanations

    securely, caps, payments

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

    input and output limits

    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
     نجي
    0.47
    Invalids
    0.44
    ical
    0.44
     नामक
    0.44
     پوچھا
    0.44
    novae
    0.43
    餮
    0.43
     انگل
    0.43
    nament
    0.43
    StructOf
    0.42
    POSITIVE LOGITS
     imidazol
    0.48
    હા
    0.47
     BUR
    0.47
     HUR
    0.47
    ल
    0.46
     executor
    0.44
    р
    0.44
    不
    0.44
    ক
    0.44
     metas
    0.44
    Activations Density 0.001%

    No Known Activations