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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73903
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

    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
     or
    -1.77
     by
    -1.65
     with
    -1.63
     came
    -1.57
     people
    -1.52
     from
    -1.51
     good
    -1.48
     out
    -1.47
     various
    -1.42
     on
    -1.41
    POSITIVE LOGITS
    unfortunately
    1.53
    theres
    1.38
    frequently
    1.38
     récupérer
    1.32
    generally
    1.32
     !!!!
    1.23
     Dinas
    1.23
    happens
    1.21
    knows
    1.21
     préparer
    1.20
    Activations Density 0.050%

    No Known Activations