© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129178
    Prev
    Next
    INDEX
    Explanations

    code block closing characters

    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
    硖
    -1.66
    ⻬
    -1.57
    ongiorno
    -1.51
     if
    -1.48
     you
    -1.48
     member
    -1.47
    癀
    -1.47
    opje
    -1.42
     maravilla
    -1.41
    凪
    -1.41
    POSITIVE LOGITS
    3
    2.22
    4
    2.03
    8
    1.93
    9
    1.87
    me
    1.73
    7
    1.70
    ......”
    1.59
    is
    1.58
    大部分
    1.57
    p
    1.55
    Activations Density 0.008%

    No Known Activations