© 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. 34-GEMMASCOPE-RES-131K
    7. 84192
    Prev
    Next
    INDEX
    Explanations

    code definitions and citations

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

    This neuron detects the “–(Type)methodName…” or “+(Type)…” syntax that marks Objective-C method declarations or definitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    perus
    -0.96
    ÍN
    -0.88
    Existence
    -0.86
     alliés
    -0.85
     wrze
    -0.84
    ценка
    -0.84
     bencana
    -0.84
    ᛏ
    -0.83
    Bigr
    -0.82
    Inspiration
    -0.82
    POSITIVE LOGITS
     ibid
    4.31
     Ibid
    4.31
    Ibid
    3.75
    ibid
    3.55
     same
    2.22
     ib
    2.08
     ditto
    2.02
    同上
    2.02
     Ibidem
    1.92
     idem
    1.90
    Activations Density 0.018%

    No Known Activations