© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3813
    Prev
    Next
    INDEX
    Explanations

    conversational interjections

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

    "Okay," response starter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     illetve
    0.18
     domain
    0.17
     amplitude
    0.17
     {\
    0.17
     neuron
    0.17
     unmittelbar
    0.17
     reeds
    0.17
     filaments
    0.16
     +(
    0.16
     ())
    0.16
    POSITIVE LOGITS
     זה
    0.27
    это
    0.25
     didn
    0.23
     לא
    0.23
     এটা
    0.22
     не
    0.22
     это
    0.22
    maybe
    0.21
     няма
    0.20
     гэта
    0.20
    Activations Density 0.320%

    No Known Activations