© 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. 127997
    Prev
    Next
    INDEX
    Explanations

    Intervention with, Guest Post

    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
    ”،
    -1.45
     anún
    -1.34
     januari
    -1.30
     Februari
    -1.27
     Januari
    -1.25
     "¿
    -1.25
    😫
    -1.24
    🤮
    -1.24
    ："
    -1.23
     pittores
    -1.23
    POSITIVE LOGITS
     our
    1.70
     all
    1.57
     each
    1.47
     some
    1.38
     those
    1.28
     every
    1.27
     others
    1.27
     not
    1.21
     most
    1.12
     other
    1.11
    Activations Density 0.002%

    No Known Activations