© 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. 11338
    Prev
    Next
    INDEX
    Explanations

    quoted technical terms

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

    opening quotation marks in technical or programming-related text.

    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
     and
    -2.78
     also
    -2.45
     or
    -2.45
     as
    -1.98
     an
    -1.96
     without
    -1.95
     a
    -1.88
     it
    -1.86
     laikā
    -1.84
     with
    -1.82
    POSITIVE LOGITS
     secluded
    1.70
     !!!!
    1.69
     molti
    1.66
    ſſen
    1.63
     revered
    1.61
     myriad
    1.56
    
    1.56
     quintessential
    1.55
     ridiculously
    1.52
     flamboyant
    1.52
    Activations Density 0.036%

    No Known Activations