© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11548
    Prev
    Next
    INDEX
    Explanations

    Initialization or assignment sequences

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

    the `Name` attribute assignment in code (particularly after the equals sign and opening quote in `Name="` patterns).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     essenciais
    -1.84
    が少ない
    -1.83
     robusto
    -1.72
     kupić
    -1.63
    ーーーー
    -1.62
     菇
    -1.60
     luminoso
    -1.51
     följande
    -1.51
     tromper
    -1.49
    ㊗
    -1.49
    POSITIVE LOGITS
     of
    2.08
     but
    1.95
     and
    1.84
    ”.
    1.71
     to
    1.66
     A
    1.59
    ON
    1.58
    
    1.55
    AN
    1.54
    AS
    1.54
    Activations Density 0.001%

    No Known Activations