© 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. 7115
    Prev
    Next
    INDEX
    Explanations

    grammatical categories and technical terms

    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
     Dioxide
    -1.42
    ↵↵
    -1.42
    }:
    -1.38
    </h5>
    -1.38
    $
    -1.36
    ↵↵↵
    -1.35
     Songtext
    -1.34
     ferv
    -1.33
    Appellee
    -1.33
    ↵↵↵↵↵
    -1.31
    POSITIVE LOGITS
    んでいます
    1.34
     работают
    1.33
    which
    1.33
    ByPrimaryKey
    1.28
    showed
    1.24
     všechny
    1.21
     totalling
    1.20
    habil
    1.19
     אנחנו
    1.17
     utilizó
    1.17
    Activations Density 0.017%

    No Known Activations