© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76143
    Prev
    Next
    INDEX
    Explanations

    actions we deem

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

    from tiny to

    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
    بعض
    0.52
    ♎
    0.51
     वर्णन
    0.48
     አይደለም
    0.47
    électricité
    0.47
     آهي
    0.47
     точек
    0.47
     بيقول
    0.47
    SETUP
    0.47
     Stuttgart
    0.46
    POSITIVE LOGITS
    as
    0.47
    ry
    0.44
    iter
    0.44
    opic
    0.44
    ilar
    0.43
    usi
    0.43
     (
    0.42
    ings
    0.42
    val
    0.42
     Iter
    0.42
    Activations Density 0.001%

    No Known Activations