© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6469
    Prev
    Next
    INDEX
    Explanations

    view critically or view others

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

    The neuron fires on short, standalone imperative or call-to-action words (e.g. “View,” “See,” “Filter,” “Browse,” “Access”) used to prompt navigation or interaction.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    ﻯ
    1.10
    ﻴ
    1.08
    ﺩ
    1.05
    Ingrese
    1.04
    Merhaba
    1.02
    Practical
    1.02
    ى
    1.00
    ﺓ
    0.97
     সমন্বয়
    0.96
    ција
    0.96
    POSITIVE LOGITS
     einiger
    0.96
    ö
    0.93
     könne
    0.91
     mieux
    0.90
     schönsten
    0.90
    isser
    0.89
    らの
    0.89
    更大的
    0.89
    ラの
    0.88
     anderen
    0.87
    Activations Density 0.040%

    No Known Activations