© 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. 6865
    Prev
    Next
    INDEX
    Explanations

    Slavic language terms

    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
    BOTTOM
    1.77
     contoured
    1.76
     hypo
    1.75
     bestimmt
    1.75
     ENVIRONMENTAL
    1.74
    clare
    1.74
    𝗨
    1.72
     inferred
    1.70
     bucket
    1.69
     зависимости
    1.68
    POSITIVE LOGITS
    anin
    1.34
    мна
    1.12
    quette
    1.08
    غول
    1.07
    renz
    1.06
    щается
    1.06
    yya
    1.05
    halle
    1.05
     NXT
    1.04
    ":{"
    1.04
    Activations Density 0.009%

    No Known Activations