© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104625
    Prev
    Next
    INDEX
    Explanations

    initials and short names

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

    The neuron fires on the numeric seed/ranking positions (three-digit or similar numeric labels) that appear in tournament player listings.

    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
    brtc
    -1.64
     miſ
    -1.57
    giaan
    -1.49
    ౧
    -1.46
     usługi
    -1.44
     monumental
    -1.42
     DIDN
    -1.42
    instein
    -1.42
     organik
    -1.40
     řešení
    -1.38
    POSITIVE LOGITS
    H
    1.69
    B
    1.68
    A
    1.62
    T
    1.58
    L
    1.53
    '
    1.53
    J
    1.51
     pysty
    1.48
     mieste
    1.44
     kokona
    1.42
    Activations Density 0.001%

    No Known Activations