© 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. 251511
    Prev
    Next
    INDEX
    Explanations

    offer information

    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
    უალ
    0.48
     despised
    0.48
    滘
    0.47
     расстоя
    0.47
     kayb
    0.47
     наре
    0.46
    Wouldn
    0.46
     возможности
    0.46
    controle
    0.45
    Rap
    0.45
    POSITIVE LOGITS
    ABC
    0.42
     IBS
    0.42
    hams
    0.42
    hose
    0.42
    MLA
    0.42
     crossovers
    0.41
    <0x80>
    0.41
    TAG
    0.41
    TagName
    0.40
    壳
    0.40
    Activations Density 0.001%

    No Known Activations