© 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. 6834
    Prev
    Next
    INDEX
    Explanations

    Protractor scripts

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

    The neuron strongly activates on numeric tokens—digits, version numbers, and other number‐containing strings (including hyphens and dots in version tags).

    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
    타
    -0.77
    }}}
    
    -0.73
    Lectures
    -0.73
     lymphoma
    -0.71
    сці
    -0.71
    chantment
    -0.69
    msk
    -0.68
    pagn
    -0.68
     熟
    -0.68
     courtship
    -0.68
    POSITIVE LOGITS
    browsers
    0.96
     launchers
    0.90
     Indianapolis
    0.84
     karma
    0.82
     Karma
    0.81
     Indy
    0.81
     browsers
    0.80
     coverage
    0.79
    frust
    0.74
    怂
    0.74
    Activations Density 0.016%

    No Known Activations