© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73413
    Prev
    Next
    INDEX
    Explanations

    79

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

    The neuron is a detector for the two‐digit number “79” (as it appears in citations, RFC numbers, DOIs, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    咴
    -2.55
    
    -2.52
     colaboradores
    -2.30
    缫
    -2.27
    
    -2.27
    鼉
    -2.20
     laatste
    -2.17
    縯
    -2.16
     vendido
    -2.14
    寔
    -2.13
    POSITIVE LOGITS
    9
    4.09
    1
    3.66
    8
    3.38
    3
    3.33
    6
    2.98
    7
    2.97
    </strong>
    2.77
    4
    2.67
     для
    2.59
    –
    2.58
    Activations Density 0.012%

    No Known Activations