© 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. 19625
    Prev
    Next
    INDEX
    Explanations

    line break characters

    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
     sabem
    -1.78
    )
    -1.72
     him
    -1.71
     those
    -1.61
     both
    -1.54
     that
    -1.50
     which
    -1.49
     dificuldade
    -1.47
     problemy
    -1.41
     even
    -1.40
    POSITIVE LOGITS
    </b>
    1.91
     détente
    1.57
    駸
    1.55
    啾
    1.52
    quels
    1.50
    洐
    1.50
    ments
    1.49
    ◻
    1.47
    ⩥
    1.47
     sobri
    1.46
    Activations Density 0.007%

    No Known Activations