© 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. 78778
    Prev
    Next
    INDEX
    Explanations

    Great Love

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

    therapist knows, means enough, hiding under

    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
     değişik
    0.50
     mame
    0.50
     appears
    0.48
    zäh
    0.48
    >]</
    0.47
     ডুব
    0.47
    ması
    0.46
    jima
    0.45
    maß
    0.45
     uzman
    0.45
    POSITIVE LOGITS
     Пари
    0.48
    Ket
    0.47
    沇
    0.47
     γά
    0.46
    聖
    0.46
    <unused206>
    0.46
    Pan
    0.45
    todos
    0.45
    PLY
    0.45
    我們會
    0.45
    Activations Density 0.001%

    No Known Activations