© 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. 79897
    Prev
    Next
    INDEX
    Explanations

    names followed by 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
     which
    -1.55
     from
    -1.50
    banez
    -1.48
    rfan
    -1.38
     אך
    -1.28
     their
    -1.27
     великолеп
    -1.24
    område
    -1.21
    閬
    -1.20
    ebly
    -1.20
    POSITIVE LOGITS
     is
    3.09
     was
    2.38
     has
    2.13
     didn
    1.87
     shouldn
    1.84
     are
    1.73
     wasn
    1.68
     have
    1.63
     always
    1.58
     will
    1.57
    Activations Density 0.023%

    No Known Activations