© 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. 44543
    Prev
    Next
    INDEX
    Explanations

    Bren, Lager, brew, TiO, BK, coke

    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
    this
    -2.88
    you
    -2.80
    v
    -2.75
    er
    -2.73
    J
    -2.69
    Ꭳ
    -2.64
    ata
    -2.53
    b
    -2.52
     ventures
    -2.41
    va
    -2.36
    POSITIVE LOGITS
    剮
    2.72
    蹀
    2.44
    ጹ
    2.41
     If
    2.41
    这件事情
    2.38
    沵
    2.28
     eleições
    2.25
    錞
    2.20
    倂
    2.20
     tombs
    2.19
    Activations Density 0.013%

    No Known Activations