© 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. 8908
    Prev
    Next
    INDEX
    Explanations

    Presentation title

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

    The neuron consistently lights up on brief multi‐word connective or elaborative chunks—especially verb–preposition pairs and noun phrases joined by conjunctions or prepositions (e.g. “thinking about,” “or Y projects,” “in, on, and around”).

    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
    مه
    0.74
     apr
    0.72
     notifications
    0.70
     menunjukkan
    0.70
    در
    0.68
     communities
    0.68
     publications
    0.66
    ાવ
    0.66
     obligations
    0.66
     authority
    0.66
    POSITIVE LOGITS
    kunst
    0.90
    сны
    0.88
    creates
    0.88
    criar
    0.88
    ⊟
    0.87
    čka
    0.83
    abá
    0.82
    ▦
    0.82
    creating
    0.82
    로우
    0.81
    Activations Density 0.000%

    No Known Activations