© 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. 11513
    Prev
    Next
    INDEX
    Explanations

    divine revelation or other options

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

    The neuron fires on longer, salient content words (nouns, verbs, and adjectives of moderate length) rather than on short function words.

    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
    ただし
    0.76
     includes
    0.75
    $,
    0.73
    }$,
    0.72
    によると
    0.71
    },
    0.70
    ちなみに
    0.69
    includes
    0.69
    %,
    0.64
    }.
    0.63
    POSITIVE LOGITS
    كنولوجيا
    0.81
     życie
    0.74
     possano
    0.74
     davvero
    0.73
     mogao
    0.73
     dapat
    0.70
     Dapat
    0.70
     Bisa
    0.70
     bisa
    0.69
    cribing
    0.68
    Activations Density 0.532%

    No Known Activations