© 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. 13845
    Prev
    Next
    INDEX
    Explanations

    abstracts and descriptions

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

    The main thing this neuron does is pick out semantically important content words—key nouns, adjectives, and past‐participle verbs that carry the core informational weight of a sentence.

    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
     bởi
    0.89
    rose
    0.71
    可怕
    0.71
    셩
    0.70
    கொ
    0.70
    otic
    0.70
    িস্ট
    0.70
    🏃
    0.70
    मान
    0.69
    に
    0.69
    POSITIVE LOGITS
     JAM
    0.81
     jedno
    0.80
     jednego
    0.76
     hire
    0.76
     tiene
    0.75
     عليك
    0.75
     思っ
    0.75
     großer
    0.74
     contiene
    0.74
    ﻀ
    0.74
    Activations Density 0.000%

    No Known Activations