© 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. 10-GEMMASCOPE-RES-131K
    7. 22553
    Prev
    Next
    INDEX
    Explanations

    shooting, hitting, serving, batting

    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
    遢
    -1.80
    軚
    -1.80
    还要
    -1.79
     bisogno
    -1.63
    褔
    -1.61
    Also
    -1.60
    However
    -1.60
    This
    -1.53
    Again
    -1.51
    Please
    -1.49
    POSITIVE LOGITS
     about
    1.80
    </h3>
    1.70
     realizando
    1.53
    驺
    1.53
     cuidadosamente
    1.48
    ätzung
    1.45
    -
    1.43
     “
    1.42
     "'
    1.41
     erlä
    1.38
    Activations Density 0.014%

    No Known Activations