© 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. 10-GEMMASCOPE-RES-131K
    7. 914
    Prev
    Next
    INDEX
    Explanations

    owned by

    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_10/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
    which
    -3.16
    ."
    -2.89
    “
    -2.86
    er
    -2.78
    0
    -2.70
    ?"
    -2.59
    e
    -2.48
    one
    -2.48
    各样的
    -2.44
     -
    -2.36
    POSITIVE LOGITS
    provides
    3.22
    colgante
    2.91
     exhilarating
    2.89
     religiosos
    2.83
     menacing
    2.80
     horrifying
    2.75
    excell
    2.70
     tht
    2.70
     lác
    2.69
     unending
    2.69
    Activations Density 0.018%

    No Known Activations