© 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. 22-GEMMASCOPE-RES-131K
    7. 33846
    Prev
    Next
    INDEX
    Explanations

    introducing additional information

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

    The neuron activates in response to numeric values and statistical figures (e.g. sample sizes, percentages, measurement readings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    
    -1.23
    苼
    -1.13
    
    -1.13
    
    -1.13
     prová
    -1.12
    要做
    -1.10
     diſt
    -1.08
    
    -1.08
     painel
    -1.07
     hipótesis
    -1.06
    POSITIVE LOGITS
    when
    1.18
     grø
    1.02
     when
    1.01
    至尊
    1.00
    ulier
    0.98
     during
    0.98
    ❄️
    0.95
    🎄
    0.95
     longstanding
    0.95
     timmar
    0.94
    Activations Density 0.082%

    No Known Activations