© 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. 25333
    Prev
    Next
    INDEX
    Explanations

    string or attribute or question

    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
     gekocht
    -0.94
    ırlar
    -0.94
     kehamilan
    -0.94
    ܣ
    -0.90
     savait
    -0.90
     requested
    -0.88
     frischen
    -0.87
     eighties
    -0.84
     lainnya
    -0.83
    Interpre
    -0.82
    POSITIVE LOGITS
    minating
    1.07
     jardim
    1.04
    ocused
    1.02
     وكذلك
    1.02
     hry
    0.98
     desenho
    0.97
     Informações
    0.97
    пратки
    0.96
    usions
    0.96
     imageNamed
    0.94
    Activations Density 0.020%

    No Known Activations