© 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. 103290
    Prev
    Next
    INDEX
    Explanations

    to VERB

    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
     
    -1.75
     one
    -1.75
    <bos>
    -1.73
     nahezu
    -1.70
     all
    -1.68
     massively
    -1.62
    During
    -1.58
     tremendously
    -1.58
     There
    -1.52
     frantic
    -1.52
    POSITIVE LOGITS
    睃
    1.87
     conster
    1.73
     aſ
    1.73
     incess
    1.67
     marseille
    1.66
     indeb
    1.63
     obsequ
    1.63
    ard
    1.63
     intermin
    1.63
    generally
    1.62
    Activations Density 0.005%

    No Known Activations