© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15547
    Prev
    Next
    INDEX
    Explanations

    code and special characters

    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
     in
    -1.27
     after
    -1.22
     this
    -1.21
     which
    -1.21
     by
    -1.20
     instead
    -1.17
     as
    -1.17
     those
    -1.13
     on
    -1.13
     only
    -1.11
    POSITIVE LOGITS
     trochę
    1.23
     rhino
    1.16
    trong
    1.09
    sightly
    1.09
     bloquer
    1.09
     Obten
    1.09
    actéristi
    1.08
    妧
    1.07
    łosi
    1.06
     lekko
    1.05
    Activations Density 0.116%

    No Known Activations