© 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. 129507
    Prev
    Next
    INDEX
    Explanations

    software/project names

    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
     longstanding
    -2.14
     moderately
    -1.91
     after
    -1.90
     high
    -1.90
     large
    -1.87
     because
    -1.76
     excessive
    -1.74
     had
    -1.73
     heightened
    -1.72
     low
    -1.70
    POSITIVE LOGITS
     to
    2.02
     interesses
    1.92
     faciliter
    1.91
     poë
    1.89
    螃
    1.80
     vetores
    1.77
     accessoire
    1.77
     diriger
    1.74
     maksi
    1.73
     charmant
    1.73
    Activations Density 0.191%

    No Known Activations