© 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. 9677
    Prev
    Next
    INDEX
    Explanations

    shell script commands

    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
     after
    -1.80
     by
    -1.78
    </i>
    -1.73
     each
    -1.70
     because
    -1.64
     but
    -1.62
     their
    -1.60
     an
    -1.59
    Примеча
    -1.59
     menyadari
    -1.59
    POSITIVE LOGITS
    }_{
    1.73
    玊
    1.69
    であ
    1.66
     evidentemente
    1.57
     sizeof
    1.55
     inférieur
    1.52
     produktów
    1.51
    韪
    1.49
    aná
    1.48
    ⩕
    1.48
    Activations Density 0.014%

    No Known Activations