© 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. 34-GEMMASCOPE-RES-131K
    7. 30853
    Prev
    Next
    INDEX
    Explanations

    error probability and rate

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

    The neuron is keyed to numerical evaluation terms, especially “error,” “probability,” “rate,” and related statistical‐metric words.

    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
    ficit
    -0.82
    콘
    -0.80
     Максима
    -0.76
    zza
    -0.74
     lingua
    -0.71
    χα
    -0.71
    Enzo
    -0.70
    uete
    -0.69
     gland
    -0.68
     europa
    -0.67
    POSITIVE LOGITS
     error
    1.72
    error
    1.26
     Error
    1.20
     errors
    1.11
     Errors
    1.09
     ERROR
    1.07
     Mistakes
    1.05
     risk
    1.01
    Error
    0.98
     mistakes
    0.97
    Activations Density 0.027%

    No Known Activations