© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73423
    Prev
    Next
    INDEX
    Explanations

    index access with brackets

    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
     that
    -1.92
     this
    -1.58
     will
    -1.38
     even
    -1.36
     που
    -1.23
     and
    -1.12
     of
    -1.12
     who
    -1.10
     with
    -1.05
     by
    -1.02
    POSITIVE LOGITS
     délicieux
    1.18
     spada
    1.14
     Efek
    1.13
    Provide
    1.08
     kompres
    1.07
    Creates
    1.05
     doivent
    1.05
     katalog
    1.03
     torba
    1.02
    gefügt
    1.00
    Activations Density 0.003%

    No Known Activations