© 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. 19608
    Prev
    Next
    INDEX
    Explanations

    Despite being

    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
     but
    -1.87
     that
    -1.51
     of
    -1.44
    partements
    -1.43
    l
    -1.40
    >
    -1.36
    </em>
    -1.33
    );
    -1.30
    ведите
    -1.27
    越高
    -1.25
    POSITIVE LOGITS
     toalha
    1.60
     pneus
    1.59
     médic
    1.52
     anún
    1.44
    gunakan
    1.41
     potes
    1.41
    臵
    1.40
    焢
    1.39
     oslo
    1.39
    esinde
    1.39
    Activations Density 0.023%

    No Known Activations