© 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. 69639
    Prev
    Next
    INDEX
    Explanations

    imports and dependencies

    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
    a
    -2.78
    1
    -2.66
    d
    -2.30
    罴
    -2.28
     видеть
    -2.25
     Other
    -2.11
    c
    -2.11
    de
    -2.11
     geprüft
    -2.09
    L
    -2.03
    POSITIVE LOGITS
    _));
    2.45
    "
    2.36
    '
    2.31
    érité
    2.30
    崃
    2.17
    祤
    2.13
    زيل
    2.08
    。"
    2.06
    BeginInit
    2.03
    魨
    2.02
    Activations Density 0.000%

    No Known Activations