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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59997
    Prev
    Next
    INDEX
    Explanations

    number or ordinal followed by word

    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
     "
    -1.81
    躄
    -1.77
     vacunas
    -1.73
    苤
    -1.73
     pertinente
    -1.66
     comptes
    -1.62
    撅
    -1.62
    噘
    -1.60
    龇
    -1.57
    镲
    -1.55
    POSITIVE LOGITS
     with
    2.16
    When
    1.91
     when
    1.88
    </i>
    1.80
     through
    1.78
    Usually
    1.76
     because
    1.70
     like
    1.67
     for
    1.66
    Sometimes
    1.66
    Activations Density 0.057%

    No Known Activations