© 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. 34-GEMMASCOPE-RES-131K
    4. 98316
    Prev
    Next
    INDEX
    Explanations

    betting picks and stakes

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

    This neuron fires on tokens that are capitalized or numeric (e.g. proper names, acronyms, domain‐style words, or standalone numbers).

    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
     Props
    -0.78
    AnchorStyles
    -0.76
    由来
    -0.76
     payout
    -0.74
    Futures
    -0.72
     props
    -0.69
     tork
    -0.69
     forms
    -0.69
    曹操
    -0.69
    덱
    -0.69
    POSITIVE LOGITS
     selections
    1.00
    Selections
    0.99
     Selections
    0.98
     stake
    0.97
     selection
    0.93
    çon
    0.84
    utation
    0.84
     biceps
    0.83
     Stake
    0.82
     staked
    0.82
    Activations Density 0.007%

    No Known Activations