© 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. 45299
    Prev
    Next
    INDEX
    Explanations

    Itanium processors

    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
     BETWEEN
    -1.43
     véritable
    -1.39
     gouverneur
    -1.37
     schließlich
    -1.34
    Huhu
    -1.33
    Controllo
    -1.30
    Between
    -1.29
    italien
    -1.25
     USING
    -1.24
    侂
    -1.24
    POSITIVE LOGITS
     they
    1.48
     from
    1.24
    ?
    1.15
     alimenti
    1.15
    。
    1.09
    </tr>
    1.05
    ↵
    1.05
     created
    1.04
    <h2>
    1.02
     only
    1.02
    Activations Density 0.156%

    No Known Activations