© 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. 128121
    Prev
    Next
    INDEX
    Explanations

    not using Node

    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
    いただきました
    -0.98
    籬
    -0.94
    となりました
    -0.92
    astronomie
    -0.88
    Così
    -0.88
     bezpeč
    -0.87
    encu
    -0.84
     rám
    -0.84
     tých
    -0.84
     nadzie
    -0.83
    POSITIVE LOGITS
    其它
    0.96
    镌
    0.91
     carlos
    0.86
    髙
    0.85
    ája
    0.84
    nością
    0.84
     tall
    0.83
    任何
    0.82
    其他的
    0.82
    药物
    0.82
    Activations Density 0.050%

    No Known Activations