© 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. 10-GEMMASCOPE-RES-131K
    7. 10050
    Prev
    Next
    INDEX
    Explanations

    takes action or consequence

    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_10/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
    0
    -3.81
    the
    -2.64
    長崎
    -2.41
    い
    -2.41
    ed
    -2.38
     of
    -2.34
    7
    -2.30
    厕所
    -2.28
    an
    -2.27
    薅
    -2.25
    POSITIVE LOGITS
     alot
    2.44
    AutoresizingMask
    2.31
    ICOLON
    2.14
    líben
    2.13
     Who
    2.13
    archiwizowane
    2.13
     Takes
    2.11
     cbd
    2.09
    分か
    2.09
     maravillosas
    2.06
    Activations Density 0.007%

    No Known Activations