© 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. 16366
    Prev
    Next
    INDEX
    Explanations

    calculation instructions and definitions

    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
     our
    -1.27
     ourselves
    -1.16
     plateforme
    -1.13
     anyways
    -1.13
    няют
    -1.11
     we
    -1.09
    actually
    -1.09
     unserer
    -1.08
     soluzione
    -1.05
    Actually
    -1.02
    POSITIVE LOGITS
    Ekster
    1.33
     when
    1.30
     frightening
    1.25
     χρησιμοποι
    1.23
     seleccionadas
    1.22
     dólares
    1.20
     maduro
    1.19
    gigabyte
    1.19
     використову
    1.19
     used
    1.19
    Activations Density 0.005%

    No Known Activations