© 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. 22-GEMMASCOPE-RES-131K
    7. 68497
    Prev
    Next
    INDEX
    Explanations

    code constructs including operators and types

    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_22/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
    はなく
    -0.93
    それにしても
    -0.92
    に関する
    -0.89
    がなく
    -0.88
     to
    -0.85
    tetur
    -0.82
    setFocusable
    -0.82
    }^{+
    -0.81
    ólico
    -0.81
    ása
    -0.79
    POSITIVE LOGITS
     bizony
    0.92
     seules
    0.89
    ője
    0.86
     bañ
    0.86
     közé
    0.85
     család
    0.84
    czego
    0.84
     Dube
    0.84
    说道
    0.83
    nexo
    0.83
    Activations Density 0.016%

    No Known Activations