© 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. 119420
    Prev
    Next
    INDEX
    Explanations

    code separators and values

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

    the letter 'f' when it appears immediately after a comma in code, particularly in numeric literals and parameter lists.

    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
    ֟
    -1.73
     gamle
    -1.73
    itemBuilder
    -1.72
     proste
    -1.67
     ruso
    -1.66
     êtres
    -1.65
     seier
    -1.64
    
    -1.63
    🃏
    -1.61
     efficace
    -1.59
    POSITIVE LOGITS
     you
    2.31
    derdag
    1.65
     When
    1.62
     and
    1.59
     absence
    1.56
    “
    1.49
    lgari
    1.48
     나는
    1.48
     entice
    1.48
     riservata
    1.47
    Activations Density 0.007%

    No Known Activations