© 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. 255
    Prev
    Next
    INDEX
    Explanations

    conjunctions and verbs

    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
     after
    -1.82
     which
    -1.76
     recently
    -1.70
     currently
    -1.63
     that
    -1.59
    Recently
    -1.48
     when
    -1.43
     actually
    -1.42
     recent
    -1.40
     who
    -1.32
    POSITIVE LOGITS
     tandis
    1.30
     devine
    1.15
     everywhere
    1.14
     zaś
    1.11
    њу
    1.09
     становится
    1.06
    と書
    1.05
     iar
    1.05
     powst
    1.04
     CORPORATION
    1.02
    Activations Density 0.034%

    No Known Activations