© 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. 15377
    Prev
    Next
    INDEX
    Explanations

    options or conditions

    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
    髋
    -0.81
     esquecer
    -0.81
     perte
    -0.80
    krę
    -0.79
     ]);
    -0.79
    ău
    -0.77
    wezig
    -0.75
    忘记
    -0.75
    ŚCI
    -0.75
    óstico
    -0.75
    POSITIVE LOGITS
     additional
    0.94
     дополнитель
    0.94
     there
    0.85
    怎麼辦
    0.85
     forced
    0.84
     resort
    0.84
     resorted
    0.81
     выну
    0.81
    extension
    0.79
    只好
    0.79
    Activations Density 0.078%

    No Known Activations