© 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. 208581
    Prev
    Next
    INDEX
    Explanations

    . idea your destinations

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

    history

    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
    તિ
    0.46
    umuza
    0.46
    VIDOR
    0.45
    TARGETTING
    0.45
     vasocon
    0.45
    잍
    0.43
     Fernanda
    0.43
     PKD
    0.43
     દવા
    0.43
     μαύ
    0.42
    POSITIVE LOGITS
    满
    0.46
    els
    0.43
    к
    0.43
    평
    0.42
    по
    0.40
    inos
    0.40
     rectas
    0.39
     like
    0.39
    ogn
    0.39
    随时
    0.39
    Activations Density 0.001%

    No Known Activations