© 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. 128025
    Prev
    Next
    INDEX
    Explanations

    police said

    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
     as
    -1.27
     for
    -1.26
     of
    -1.16
     what
    -1.13
     alongside
    -1.05
    :
    -0.99
     sooooo
    -0.97
     (
    -0.96
     by
    -0.93
     considerably
    -0.93
    POSITIVE LOGITS
     extraer
    1.20
    läs
    1.19
    lorn
    1.18
    耷
    1.13
    zembro
    1.13
    どうも
    1.09
    gangss
    1.09
    THANK
    1.07
     Ս
    1.07
    Criminal
    1.06
    Activations Density 0.025%

    No Known Activations