© 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. 10-GEMMASCOPE-RES-131K
    7. 58773
    Prev
    Next
    INDEX
    Explanations

    min, MIN_

    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
    ↵
    -3.44
    ↵↵
    -3.06
     Roughly
    -3.03
     Primarily
    -2.98
     Relatively
    -2.94
     Certainly
    -2.86
     Not
    -2.81
     Historically
    -2.77
     Undoubtedly
    -2.70
     Normally
    -2.69
    POSITIVE LOGITS
    a
    3.78
    s
    3.34
    釓
    3.25
    _
    3.25
    your
    3.19
    at
    3.05
    m
    2.97
    ا
    2.77
    is
    2.75
    ቬ
    2.75
    Activations Density 0.001%

    No Known Activations