© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14869
    Prev
    Next
    INDEX
    Explanations

    dependent on

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

    The neuron flags semantically “heavy” content words—key topical terms and nouns or verbs carrying core meaning.

    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
     със
    0.73
    包括
    0.72
    唆
    0.70
    или
    0.70
    उदा
    0.66
     вместо
    0.65
     such
    0.64
    например
    0.64
     например
    0.63
    Դ
    0.63
    POSITIVE LOGITS
     YOU
    0.98
     Depends
    0.98
     depende
    0.93
     depends
    0.88
    YOU
    0.86
    手間
    0.82
     dipende
    0.82
     guesswork
    0.81
    hört
    0.80
     letzt
    0.80
    Activations Density 0.530%

    No Known Activations