© 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. 44642
    Prev
    Next
    INDEX
    Explanations

    authenticated user or logged in

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

    current logged-in user authentication

    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
     друзей
    0.48
    好友
    0.46
     ጎ
    0.44
     примерно
    0.43
    👤
    0.43
     alrededor
    0.43
     вокруг
    0.43
     বন্ধুদের
    0.43
    创始人
    0.43
     جاي
    0.43
    POSITIVE LOGITS
     photons
    0.44
    ಷ
    0.43
    дження
    0.42
    omas
    0.42
     probabilidades
    0.41
    OMAS
    0.40
     qubits
    0.40
     acted
    0.39
     pectin
    0.39
     dioxygen
    0.39
    Activations Density 0.000%

    No Known Activations