© 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. 2425
    Prev
    Next
    INDEX
    Explanations

    coding and technology concepts

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

    The neuron strongly lights up on key abstract nouns and concept-words (e.g. demands, actions, opportunity, duties, communication)—i.e. it detects important content-bearing nouns.

    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
    F
    0.97
     caída
    0.96
    ﺪ
    0.95
    ﮯ
    0.93
     linha
    0.89
    W
    0.88
    ﺰ
    0.87
    du
    0.87
    cellulose
    0.87
    ﻥ
    0.87
    POSITIVE LOGITS
     scallop
    0.55
    न्न
    0.55
    йде
    0.54
    TINGS
    0.54
     organization
    0.52
     tricks
    0.52
    hing
    0.52
     generic
    0.52
    род
    0.51
     authorizations
    0.51
    Activations Density 0.000%

    No Known Activations