© 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. 60447
    Prev
    Next
    INDEX
    Explanations

    speaking or telling

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

    The neuron fires on informal conversational or rhetorical speech‐act phrases—especially things like “I tell you,” “you can tell,” “ask anyone,” “can’t deny,” etc.

    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
     отметил
    -0.96
    thyl
    -0.82
    umbu
    -0.82
     jardim
    -0.81
    stated
    -0.81
    iora
    -0.78
    Provides
    -0.78
     couleurs
    -0.77
     turbine
    -0.77
    看他
    -0.76
    POSITIVE LOGITS
     tell
    7.81
     telling
    6.53
     tells
    6.53
     told
    6.22
     Tell
    6.19
    Tell
    6.09
    tell
    5.56
     TELL
    4.78
    告诉
    4.78
    TELL
    4.59
    Activations Density 0.347%

    No Known Activations