© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116150
    Prev
    Next
    INDEX
    Explanations

    software and documentation

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

    The neuron fires most strongly on action‐oriented tokens—especially “help,” “find,” “service,” and the infinitival marker “to”—i.e. words that introduce or signal a call to action.

    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
     Flucht
    -0.88
     citizenship
    -0.85
     рестай
    -0.79
    では
    -0.76
    cen
    -0.74
    ἔ
    -0.74
     sins
    -0.74
    lä
    -0.73
    Chall
    -0.73
    generation
    -0.73
    POSITIVE LOGITS
    ค
    1.21
     đêm
    0.89
    Sah
    0.85
    Discovery
    0.85
    arh
    0.84
    нинг
    0.81
    ويل
    0.80
    :--
    0.79
     sorgfältig
    0.79
     Vah
    0.78
    Activations Density 0.007%

    No Known Activations