© 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. 95451
    Prev
    Next
    INDEX
    Explanations

    programming commands and symbols

    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
     konflikt
    -1.12
    цент
    -0.98
    помо
    -0.94
    ettbewerb
    -0.94
     identifiant
    -0.93
    век
    -0.93
     tiroirs
    -0.93
     geheim
    -0.92
     kaart
    -0.90
     frasco
    -0.90
    POSITIVE LOGITS
     rect
    0.89
     領
    0.87
    其他的
    0.82
     reds
    0.81
    过来的
    0.81
    ];
    0.80
    Minden
    0.80
     secolo
    0.79
    jacke
    0.79
    みよう
    0.79
    Activations Density 0.001%

    No Known Activations