© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103844
    Prev
    Next
    INDEX
    Explanations

    Michigan App, Rapids, Township

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

    The neuron fires on in‐text numeric reference markers (superscripted citation or footnote numbers).

    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
    
    -2.63
    他們的
    -2.58
    谖
    -2.34
     構造
    -2.33
    銫
    -2.31
    诹
    -2.30
    鎘
    -2.25
     "
    -2.25
    釹
    -2.22
     erweitert
    -2.20
    POSITIVE LOGITS
     Rapids
    2.41
    釭
    2.39
    riffen
    2.31
    忖
    2.23
    nthe
    2.19
    .
    2.17
    蠖
    2.16
    
    2.14
     The
    2.13
     avantage
    2.11
    Activations Density 0.003%

    No Known Activations