© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 677
    Prev
    Next
    INDEX
    Explanations

    quotation marks

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

    This neuron responds strongly to content words (non‐function words) such as nouns, verbs, and adjectives rather than common grammatical “stop” 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
     and
    0.75
     மற்றும்
    0.72
     и
    0.67
    และ
    0.66
    และการ
    0.63
    和
    0.63
     եւ
    0.60
     एवं
    0.60
     और
    0.59
     和
    0.59
    POSITIVE LOGITS
    指的是
    0.74
    abhuto
    0.74
    っていう
    0.71
     implies
    0.71
     artinya
    0.71
    というのは
    0.71
    的意思
    0.70
    意思是
    0.70
    이라는
    0.69
     heißt
    0.69
    Activations Density 0.015%

    No Known Activations