© 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. 22-GEMMASCOPE-RES-131K
    7. 128356
    Prev
    Next
    INDEX
    Explanations

    operating hours and admission

    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_22/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
    J
    -1.31
    T
    -1.13
     العاده
    -1.13
     surtout
    -1.07
     Especially
    -1.05
    _
    -1.01
     новая
    -0.99
    P
    -0.98
    B
    -0.95
     plutôt
    -0.94
    POSITIVE LOGITS
    🙈
    1.16
    😶
    1.11
    😞
    1.10
    ULATIONS
    1.09
    🥵
    1.07
    💁
    1.07
     and
    1.06
    😱
    1.05
    fl
    1.03
    íp
    1.02
    Activations Density 0.251%

    No Known Activations