© 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. 12-GEMMASCOPE-2-RES-16K
    7. 3306
    Prev
    Next
    INDEX
    Explanations

    Yes, I am

    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_12_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
    hydrocèle
    2.43
    <unused1871>
    2.38
    <unused463>
    2.35
    jiwarl
    2.35
    𒈗
    2.34
    𒇽
    2.32
    𒆳
    2.32
    𒄩
    2.29
    𒄑
    2.29
    <unused1866>
    2.29
    POSITIVE LOGITS
    .
    5.42
    。
    4.36
    !
    3.99
    ;
    3.89
    .)
    3.77
    ).
    3.72
    ।
    3.56
    .]
    3.49
    )
    3.40
    ?
    3.39
    Activations Density 0.296%

    No Known Activations