© 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. 73998
    Prev
    Next
    INDEX
    Explanations

    javascript module imports

    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
     mesma
    -0.78
    环境
    -0.76
     этих
    -0.76
    ♾
    -0.75
     מכל
    -0.75
    readyState
    -0.75
     disposição
    -0.75
     нагруз
    -0.74
    Will
    -0.73
    </em>
    -0.73
    POSITIVE LOGITS
    Dibrom
    0.92
     bőr
    0.88
     partidas
    0.85
     veldig
    0.84
     novembro
    0.84
    мерть
    0.82
    حيح
    0.81
     vence
    0.81
    Kval
    0.81
    assertj
    0.80
    Activations Density 0.056%

    No Known Activations