© 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. 57669
    Prev
    Next
    INDEX
    Explanations

    links, Reference, Tax related phrases

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

    goals and structures

    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
     кора
    0.52
     전부
    0.50
    READER
    0.46
     ڕ
    0.45
    voli
    0.45
    റ്റർ
    0.44
     disorganized
    0.42
     diesen
    0.41
     नाव
    0.41
    turn
    0.41
    POSITIVE LOGITS
    y
    0.57
    Va
    0.52
    Sau
    0.50
    yendo
    0.50
    Skin
    0.49
    >:
    0.48
    k
    0.48
     Size
    0.48
     Str
    0.47
    Sky
    0.47
    Activations Density 0.000%

    No Known Activations