© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6863
    Prev
    Next
    INDEX
    Explanations

    static final typing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    ⇑
    2.06
     nematode
    2.04
    enseignement
    2.03
    punch
    2.03
     ανθ
    2.01
     salvage
    1.98
    ď
    1.98
    essai
    1.97
    classify
    1.97
    csname
    1.96
    POSITIVE LOGITS
     readonly
    0.77
    큼
    0.74
     LOUIS
    0.69
     Buick
    0.63
    yor
    0.63
    hev
    0.63
    hattan
    0.62
    hetically
    0.59
    州市
    0.57
     Blot
    0.57
    Activations Density 0.000%

    No Known Activations