© 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. 95445
    Prev
    Next
    INDEX
    Explanations

    large group

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

    patient states and unusual behavior

    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
    s
    0.65
    ים
    0.56
    h
    0.54
    Comparator
    0.50
     Journalists
    0.49
    Water
    0.49
    avip
    0.48
    텃
    0.48
    Man
    0.48
    manip
    0.48
    POSITIVE LOGITS
    Ϳ
    0.51
     diminishes
    0.46
     সৌম
    0.44
     समाजा
    0.44
     ridicu
    0.44
     deem
    0.44
     jeder
    0.43
     révolution
    0.43
     вважа
    0.42
     overcrow
    0.42
    Activations Density 0.003%

    No Known Activations