© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25210
    Prev
    Next
    INDEX
    Explanations

    programming function definitions

    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
    8
    -1.19
    そういった
    -1.15
    というと
    -1.13
    6
    -1.05
    2
    -1.05
    4
    -1.05
    9
    -1.04
    7
    -1.04
     üblichen
    -1.04
    Specifik
    -1.04
    POSITIVE LOGITS
     your
    1.34
    ۱
    1.25
    _;
    1.25
    ﴾
    1.24
    𝑥
    1.16
    १
    1.12
    〉
    1.12
     août
    1.10
    insets
    1.09
     décembre
    1.07
    Activations Density 0.018%

    No Known Activations