© 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. 70142
    Prev
    Next
    INDEX
    Explanations

    device cost, video, spare

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

    father, mother, son, tribe

    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
    şık
    0.55
     обычной
    0.52
    steering
    0.51
     சாதாரண
    0.50
    mites
    0.50
     glLightfv
    0.50
    ⛸
    0.49
    ണ്ണി
    0.48
    transforms
    0.48
    köz
    0.48
    POSITIVE LOGITS
    D
    0.70
    T
    0.69
    E
    0.67
    G
    0.63
    P
    0.62
    A
    0.59
     de
    0.58
    M
    0.57
    I
    0.56
    C
    0.56
    Activations Density 0.001%

    No Known Activations