© 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. 22-GEMMASCOPE-RES-131K
    7. 129460
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.27
    ようになる
    -1.27
     when
    -1.20
     from
    -1.20
     indique
    -1.16
     its
    -1.10
     has
    -1.09
    」，
    -1.03
    };
    -1.03
     These
    -1.03
    POSITIVE LOGITS
    がありますが
    1.37
    but
    1.34
    もありますが
    1.21
    <bos>
    1.20
    eping
    1.15
    と思った
    1.14
     wam
    1.14
    ebly
    1.13
     but
    1.13
    particularly
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.