© 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. 72098
    Prev
    Next
    INDEX
    Explanations

    these categories or examples

    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
     تصریح
    -0.93
     εκεί
    -0.91
    ิม
    -0.88
     такое
    -0.85
    damente
    -0.85
    那样
    -0.84
    ذلك
    -0.83
     celle
    -0.83
     motivos
    -0.82
    Tembelea
    -0.82
    POSITIVE LOGITS
     these
    2.97
     below
    2.14
    these
    1.92
     These
    1.85
     listed
    1.80
     этих
    1.76
     onderstaande
    1.70
    These
    1.69
     estos
    1.66
     THESE
    1.66
    Activations Density 0.166%

    No Known Activations