© 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. 65419
    Prev
    Next
    INDEX
    Explanations

    sufficient, enough, adequacy

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

    The neuron fires on specialized technical or scientific jargon terms, such as domain‐specific keywords in photography, ventilation, clinical trials, and similar contexts.

    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
     Accuracy
    -0.84
    Karakter
    -0.82
     Maximum
    -0.82
     massimo
    -0.81
    Igles
    -0.79
     kelle
    -0.77
     wants
    -0.76
     Wants
    -0.76
    accuracy
    -0.75
     பய
    -0.74
    POSITIVE LOGITS
     sufficient
    1.67
    sufficient
    1.63
     enough
    1.63
     Sufficient
    1.48
     suficiente
    1.48
     đủ
    1.47
     sufficiency
    1.44
     adequacy
    1.35
     suffisamment
    1.30
     suffic
    1.29
    Activations Density 0.176%

    No Known Activations