© 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. 10-GEMMASCOPE-RES-131K
    7. 124696
    Prev
    Next
    INDEX
    Explanations

    rankings and competition results

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

    The neuron flags mentions of competition stages or rounds (e.g. "Quarter," "Semifinals," "First Round," "Finals").

    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
    才可以
    -1.80
     båda
    -1.74
    蹿
    -1.51
     beide
    -1.45
     participer
    -1.45
     diminuer
    -1.44
    我可以
    -1.39
    Again
    -1.38
     begge
    -1.38
     newfound
    -1.36
    POSITIVE LOGITS
     at
    1.77
     for
    1.75
     by
    1.73
     in
    1.71
    there
    1.67
     during
    1.65
     one
    1.63
     because
    1.62
     but
    1.56
     on
    1.55
    Activations Density 0.018%

    No Known Activations