© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9119
    Prev
    Next
    INDEX
    Explanations

    imaging and analysis methods

    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
     razonable
    -1.47
    </tr>
    -1.42
    (/^
    -1.41
     whom
    -1.38
     there
    -1.37
     будь
    -1.37
     whose
    -1.34
     with
    -1.30
    engagent
    -1.30
     nawet
    -1.30
    POSITIVE LOGITS
    </em>
    1.40
    引用元
    1.37
    颔
    1.35
    翃
    1.34
     Chapitre
    1.33
     manuelle
    1.30
     sowohl
    1.30
     the
    1.30
     results
    1.27
    ſch
    1.27
    Activations Density 0.787%

    No Known Activations