© 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. 32914
    Prev
    Next
    INDEX
    Explanations

    compound noun phrases

    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
    asking
    -1.34
    primarily
    -1.28
    extremely
    -1.27
    Merken
    -1.25
    despite
    -1.20
    bringing
    -1.20
    夘
    -1.20
     SPECIFIC
    -1.19
    specifically
    -1.19
     particules
    -1.17
    POSITIVE LOGITS
     It
    1.57
     or
    1.52
     Some
    1.44
     With
    1.43
     There
    1.29
     To
    1.29
    úcia
    1.27
    The
    1.27
     One
    1.27
    To
    1.25
    Activations Density 0.080%

    No Known Activations