© 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. 60959
    Prev
    Next
    INDEX
    Explanations

    positive progress evaluations

    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
    </b>
    -1.82
     there
    -1.77
     STILL
    -1.62
     proveniente
    -1.61
    </td>
    -1.55
    有大
    -1.52
    有不少
    -1.47
    qtt
    -1.38
    𝟏
    -1.37
    elernt
    -1.33
    POSITIVE LOGITS
    我们
    1.66
     antworte
    1.42
     badania
    1.42
     Our
    1.41
    ."
    1.38
    )
    1.35
    レーター
    1.31
     Geschäfte
    1.31
    ين
    1.30
     wichtig
    1.30
    Activations Density 0.014%

    No Known Activations