© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99960
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     its
    -1.91
     его
    -1.52
     encontr
    -1.49
    它的
    -1.49
     znajdu
    -1.46
    <bos>
    -1.45
    urlopen
    -1.41
    ).
    -1.40
    archiviato
    -1.39
    )、
    -1.36
    POSITIVE LOGITS
     goud
    1.52
    🐼
    1.42
     maten
    1.34
     guider
    1.34
     estadounid
    1.29
     vencedor
    1.27
     CONCLUS
    1.27
     ナイロン
    1.26
     prenn
    1.24
     insec
    1.23
    Activations Density 0.104%

    No Known Activations