© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9038
    Prev
    Next
    INDEX
    Explanations

    (*

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

    The neuron flags words that begin new clauses or sentences—especially pronouns (“he,” “you”) or imperative verbs (“Introduce,” “apologize”) right after a punctuation break.

    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
     Partnerships
    0.91
    ﺓ
    0.82
    คร
    0.77
     trotzdem
    0.77
     Subsidi
    0.77
    ^{*}(
    0.76
    thia
    0.75
    ৩৪
    0.74
     (|
    0.73
    ဘူး
    0.73
    POSITIVE LOGITS
    oe
    0.81
    ار
    0.77
    otor
    0.73
    وهات
    0.73
    比如说
    0.71
     anal
    0.71
    otts
    0.70
     pagos
    0.68
    ores
    0.66
    rences
    0.66
    Activations Density 0.001%

    No Known Activations