© 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. 130295
    Prev
    Next
    INDEX
    Explanations

    carried out

    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
    ίες
    -0.90
     която
    -0.89
    ที่
    -0.89
     ducha
    -0.87
    '];
    -0.87
    PRESSION
    -0.85
    ulus
    -0.84
    jidad
    -0.84
    āng
    -0.84
    )];
    -0.83
    POSITIVE LOGITS
     recieved
    0.97
     erhö
    0.96
     itong
    0.96
     apparti
    0.93
     sebagainya
    0.93
     carinho
    0.92
    ongeza
    0.91
     贴
    0.90
     obligaciones
    0.90
    ütün
    0.88
    Activations Density 0.001%

    No Known Activations