© 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. 119180
    Prev
    Next
    INDEX
    Explanations

    introduces items or questions

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

    This neuron detects long runs of punctuation characters (e.g. lines of repeated dashes or similar symbols) used as section or block separators.

    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
    elesai
    -0.78
    voix
    -0.75
     patata
    -0.71
    طار
    -0.71
    olio
    -0.70
    ždý
    -0.70
     koš
    -0.69
    齁
    -0.69
    ductor
    -0.68
    série
    -0.68
    POSITIVE LOGITS
    reform
    0.78
    Ignored
    0.77
     endogenous
    0.75
     دیگه
    0.73
    BeginContext
    0.73
     foc
    0.73
    ubi
    0.72
    fo
    0.72
    aried
    0.72
    考えると
    0.71
    Activations Density 0.000%

    No Known Activations