© 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. 227577
    Prev
    Next
    INDEX
    Explanations

    multilingual descriptions

    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
    reh
    0.50
    them
    0.50
    u
    0.50
    ش
    0.50
    휴
    0.49
    waste
    0.47
     medži
    0.46
    radical
    0.46
    ла
    0.46
    Mater
    0.46
    POSITIVE LOGITS
     等
    0.52
     Conversation
    0.51
     Disposition
    0.46
     Beschreibung
    0.45
     Während
    0.45
    meldung
    0.45
     对
    0.45
     Deg
    0.44
     অধিক
    0.44
     Burg
    0.44
    Activations Density 0.001%

    No Known Activations