© 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. 59558
    Prev
    Next
    INDEX
    Explanations

    JQGrid

    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
    नलोड
    -3.55
    lossians
    -3.55
    इटम
    -3.13
    尛
    -3.11
    戬
    -3.05
    鋮
    -2.98
     bestehende
    -2.86
     Auswirkungen
    -2.84
    谞
    -2.83
    ሷ
    -2.80
    POSITIVE LOGITS
    (
    3.38
    *
    3.34
    '
    3.19
    z
    3.00
    j
    2.92
    am
    2.78
    ra
    2.67
    <
    2.67
    i
    2.59
    or
    2.58
    Activations Density 0.007%

    No Known Activations