© 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. 14173
    Prev
    Next
    INDEX
    Explanations

    training

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

    The neuron strongly activates on occurrences of the word “training” (in any case or context).

    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
     only
    -2.20
     first
    -2.02
     There
    -1.73
     all
    -1.67
     $
    -1.66
     out
    -1.65
     had
    -1.52
     epitom
    -1.50
     When
    -1.49
     cleverly
    -1.46
    POSITIVE LOGITS
    毉
    1.71
    洐
    1.66
    廰
    1.63
     rimasto
    1.59
     efec
    1.55
    ラブ
    1.53
    ﻂ
    1.53
    arsi
    1.53
    CÓMO
    1.50
    こともあります
    1.50
    Activations Density 0.026%

    No Known Activations