© 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. 245685
    Prev
    Next
    INDEX
    Explanations

    states, roles, classifications

    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
     détaillée
    0.50
    цами
    0.49
    рые
    0.48
     définie
    0.48
     destinés
    0.47
    یدہ
    0.47
     département
    0.46
    ዱ
    0.46
     yì
    0.46
     circulaire
    0.46
    POSITIVE LOGITS
    itin
    0.50
    kon
    0.49
    。,
    0.49
    kinase
    0.48
    encan
    0.48
    mat
    0.48
    amples
    0.48
    thione
    0.47
    kit
    0.46
    weeks
    0.46
    Activations Density 0.001%

    No Known Activations