© 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. 34-GEMMASCOPE-RES-131K
    7. 73746
    Prev
    Next
    INDEX
    Explanations

    excel formulas and code

    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_34/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
    poll
    -0.85
     poll
    -0.82
     Duke
    -0.77
     televisor
    -0.76
    )%
    -0.75
    asymp
    -0.75
    catchError
    -0.74
     audience
    -0.74
    ="%
    -0.74
    varing
    -0.73
    POSITIVE LOGITS
     maha
    0.84
     最終
    0.83
     Enti
    0.82
    Enti
    0.80
    ナナ
    0.79
     pasting
    0.79
    味噌汁
    0.78
     Coping
    0.77
     GAC
    0.76
     Laissez
    0.75
    Activations Density 0.068%

    No Known Activations