© 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. 15245
    Prev
    Next
    INDEX
    Explanations

    winning titles and awards

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

    The neuron is triggered by numeric tokens that quantify outcomes—scores, titles, awards, vote counts, or other statistical figures.

    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
    habited
    -1.34
     มัน
    -1.29
     裸
    -1.23
     perché
    -1.21
     berbagai
    -1.20
     žiad
    -1.17
    @"
    -1.13
     แต่
    -1.12
    datable
    -1.12
     และ
    -1.11
    POSITIVE LOGITS
     first
    1.55
     one
    1.26
     all
    1.23
    brania
    1.20
     Needed
    1.20
    -
    1.20
     needed
    1.19
     only
    1.18
     gestartet
    1.16
    ühen
    1.15
    Activations Density 0.030%

    No Known Activations