© 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. 66481
    Prev
    Next
    INDEX
    Explanations

    evolution and transformation

    np_acts-logits-general · gemini-2.5-flash-lite

    verbs related to gradual changes or transformations (evolve, shrink, swell, deteriorate, close, etc.).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     of
    -2.48
    _
    -1.70
    al
    -1.45
     GOtt
    -1.45
    that
    -1.43
     folosi
    -1.42
    為に
    -1.41
    hi
    -1.40
    呸
    -1.34
     alimentare
    -1.31
    POSITIVE LOGITS
     in
    2.34
     into
    2.11
     with
    2.09
     on
    2.02
     from
    1.75
     as
    1.68
     histó
    1.66
    
    1.63
    
    1.61
     сс
    1.59
    Activations Density 0.175%

    No Known Activations