© 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. 33093
    Prev
    Next
    INDEX
    Explanations

    automotive, Consumer, effects

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

    The neuron strongly activates on numeric tokens and version-style number sequences (e.g. standalone digits, multi-digit numbers, and version identifiers).

    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
    unified
    -0.75
     unified
    -0.75
    營
    -0.73
    cts
    -0.73
    涧
    -0.71
     unidentified
    -0.71
     Wilk
    -0.70
     बाल
    -0.70
    CRL
    -0.69
    대한
    -0.67
    POSITIVE LOGITS
     político
    0.82
    כות
    0.79
     monarchy
    0.78
    插件
    0.78
     Golden
    0.75
    artement
    0.71
     vàng
    0.70
     honeymoon
    0.69
    userManager
    0.69
     ≤
    0.68
    Activations Density 0.036%

    No Known Activations