© 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. 181762
    Prev
    Next
    INDEX
    Explanations

    brothers, like, treating him

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

    solar system and political territories

    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
    firetruck
    0.59
    \%)
    0.53
    InfoHeader
    0.52
    urul
    0.52
    arena
    0.51
    nemouth
    0.51
    рих
    0.51
    ೆಂ
    0.49
    elize
    0.48
     citado
    0.48
    POSITIVE LOGITS
    ↵
    0.67
     Already
    0.49
     AVI
    0.47
    মান
    0.46
     We
    0.46
    اب
    0.46
     First
    0.46
     =
    0.46
     Local
    0.45
     STR
    0.45
    Activations Density 0.001%

    No Known Activations