© 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. 34-GEMMASCOPE-RES-131K
    7. 84307
    Prev
    Next
    INDEX
    Explanations

    bits and flags

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

    The neuron fires on programming‐style identifiers—especially uppercase or all‐caps names like macros, type names, and constants.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ชื่อ
    -0.82
    mathrm
    -0.79
    ْم
    -0.76
    essore
    -0.75
     stoichio
    -0.73
    appi
    -0.73
    每天
    -0.73
    Greetings
    -0.72
    Transcription
    -0.72
    fromUtf
    -0.71
    POSITIVE LOGITS
     mask
    2.41
    mask
    2.17
    Mask
    1.92
     bit
    1.91
     flags
    1.91
     Mask
    1.89
     masks
    1.88
     bits
    1.83
    MASK
    1.80
    bits
    1.72
    Activations Density 0.066%

    No Known Activations