© 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. 88463
    Prev
    Next
    INDEX
    Explanations

    representation of

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

    questions about what

    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
     машинасы
    0.52
     Coaching
    0.51
    分鐘
    0.50
     spør
    0.48
     Approach
    0.47
    ricks
    0.47
    眝
    0.47
     regelmatig
    0.46
     Betting
    0.46
    he
    0.46
    POSITIVE LOGITS
    CLUSTERED
    0.49
    нул
    0.49
    áticas
    0.47
    ມ
    0.47
    usky
    0.46
     gypsum
    0.45
     femoral
    0.45
    ataire
    0.45
    eled
    0.44
    étaient
    0.44
    Activations Density 0.000%

    No Known Activations