© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14473
    Prev
    Next
    INDEX
    Explanations

    `@Id` or `PRIMARY KEY` declarations

    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
    existsSync
    -0.89
     tylko
    -0.86
    titute
    -0.84
     الخام
    -0.83
     vamos
    -0.83
    kunde
    -0.82
    erba
    -0.82
     może
    -0.82
     или
    -0.82
    jonas
    -0.82
    POSITIVE LOGITS
     کوچک
    1.05
     découvrez
    0.96
     espes
    0.94
     agujeros
    0.93
     adopter
    0.93
     revisor
    0.91
    賒
    0.91
     bril
    0.91
     onlar
    0.91
    Combination
    0.89
    Activations Density 0.007%

    No Known Activations