© 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. 64772
    Prev
    Next
    INDEX
    Explanations

    annually, numerous

    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
     only
    -1.56
     two
    -1.42
     that
    -1.23
     moderately
    -1.23
     problems
    -1.13
     slightly
    -1.13
     people
    -1.09
     just
    -1.08
     meticulous
    -1.06
     these
    -1.05
    POSITIVE LOGITS
    various
    3.09
     various
    2.64
     diversos
    2.55
    Various
    2.53
     여러
    2.42
     VARIOUS
    2.41
     vários
    2.39
     myriad
    2.22
     varied
    2.20
     varies
    2.19
    Activations Density 0.152%

    No Known Activations