© 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. 25212
    Prev
    Next
    INDEX
    Explanations

    technical terms and code elements

    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
    othes
    -1.27
     insiste
    -1.24
     visites
    -1.23
    creates
    -1.23
     garante
    -1.22
     listes
    -1.21
     mantend
    -1.21
     CREATED
    -1.20
    primarily
    -1.20
     BEAUT
    -1.20
    POSITIVE LOGITS
     Each
    1.13
     The
    1.08
     Also
    1.08
    ８
    1.08
    ၀
    1.05
    Also
    1.03
     This
    1.03
     which
    1.02
     klachten
    1.02
     Using
    1.01
    Activations Density 0.026%

    No Known Activations