© 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. 118945
    Prev
    Next
    INDEX
    Explanations

    course of

    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
    </b>
    -3.11
    镡
    -1.95
    (
    -1.91
    ぶつ
    -1.88
     them
    -1.82
    ⎚
    -1.80
    荷物
    -1.80
    la
    -1.77
     suministros
    -1.75
     logros
    -1.66
    POSITIVE LOGITS
     Because
    2.31
     klarer
    1.90
     konkrete
    1.88
     It
    1.83
    aneers
    1.81
    荏
    1.80
     After
    1.76
    With
    1.76
    okovic
    1.71
    𐄁
    1.70
    Activations Density 0.006%

    No Known Activations