© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1015
    Prev
    Next
    INDEX
    Explanations

    issued to

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

    This neuron detects standalone numeric tokens (digits) used in citations or parenthetical references.

    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
    졸
    -0.75
    čet
    -0.71
     receive
    -0.71
    ͝
    -0.71
     Valkyrie
    -0.70
    müş
    -0.70
     Moscow
    -0.69
    вью
    -0.69
     mariscos
    -0.68
    Preg
    -0.67
    POSITIVE LOGITS
     jesteśmy
    0.82
     ks
    0.74
    
    0.73
    ্ট
    0.72
     camel
    0.71
    ticks
    0.71
    の発
    0.70
    fear
    0.69
    đe
    0.67
    icto
    0.67
    Activations Density 0.036%

    No Known Activations