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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13969
    Prev
    Next
    INDEX
    Explanations

    alright, fine, good, well

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

    This neuron flags words that occur in direct speech (i.e. inside quotation marks), effectively detecting spoken dialogue.

    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
    म
    0.53
    我們會
    0.52
    每次
    0.52
    م
    0.52
    in
    0.50
    아
    0.50
    мна
    0.50
     at
    0.49
     on
    0.49
    ка
    0.49
    POSITIVE LOGITS
     senyawa
    0.68
    }$&$-
    0.64
     pequeñas
    0.64
     "*************
    0.63
     ؟
    0.63
     enzimas
    0.63
     ماما
    0.63
     mutta
    0.62
     moléculas
    0.62
     ossia
    0.61
    Activations Density 0.027%

    No Known Activations