© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16043
    Prev
    Next
    INDEX
    Explanations

    other options and justifications

    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
    velli
    -0.84
    ギリ
    -0.82
    ーツ
    -0.80
    湳
    -0.78
    要注意
    -0.77
    mischen
    -0.77
    したが
    -0.76
     but
    -0.76
    其妙
    -0.75
    異なります
    -0.75
    POSITIVE LOGITS
     alternatives
    2.19
     alternative
    1.98
    alternatives
    1.80
     otherwise
    1.68
     Alternatives
    1.67
    alternative
    1.66
     alternativa
    1.59
    Alternatives
    1.55
     other
    1.52
     alternatively
    1.45
    Activations Density 0.039%

    No Known Activations