© 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. 9355
    Prev
    Next
    INDEX
    Explanations

    end of clause

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

    The neuron fires strongly on meta‐linguistic reporting cues—words that introduce or attribute speech or writing (e.g. “in an interview,” “he said in a press briefing,” “written by,” “authored,” “announced,” etc.).

    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
    з
    0.78
     зара
    0.74
    ную
    0.65
    in
    0.65
     founded
    0.64
    】：
    0.63
    Founded
    0.62
    u
    0.62
     enjoying
    0.61
    类型的
    0.61
    POSITIVE LOGITS
    टीना
    0.86
     kaha
    0.85
     tých
    0.84
    یە
    0.82
    ᓵ
    0.82
    screenWidth
    0.81
     gifs
    0.80
     rufo
    0.80
     නිෂ්
    0.80
    InCategory
    0.79
    Activations Density 0.000%

    No Known Activations