© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84795
    Prev
    Next
    INDEX
    Explanations

    tell me, tell us, telltale

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

    This neuron detects occurrences of the verb “tell” (as in “Tell me,” “Tell us,” etc.), i.e. imperative prompts requesting more information.

    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
     of
    -0.79
     пом
    -0.78
     findest
    -0.73
     чу
    -0.72
    ペース
    -0.71
    webapp
    -0.71
    IRMED
    -0.71
     то
    -0.70
    一致
    -0.68
     natürlichen
    -0.68
    POSITIVE LOGITS
    tale
    1.29
     Tell
    1.28
    Tell
    1.24
     TELL
    1.17
    tell
    1.08
     tell
    1.01
     テ
    0.96
    uride
    0.96
    ervo
    0.93
    TELL
    0.93
    Activations Density 0.008%

    No Known Activations