© 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. 112385
    Prev
    Next
    INDEX
    Explanations

    EEA, biennial, lute

    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
    ৢ
    -2.81
    流
    -2.80
    🗹
    -2.78
    咴
    -2.72
    OUTUBE
    -2.70
    akterysty
    -2.70
    xnn
    -2.67
     güne
    -2.64
    widetext
    -2.61
     日常
    -2.52
    POSITIVE LOGITS
    '
    5.94
    r
    4.50
    2
    4.19
    3
    4.13
    c
    4.09
    4
    4.06
    y
    3.94
    7
    3.67
    u
    3.61
    as
    3.59
    Activations Density 0.010%

    No Known Activations