© 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. 11564
    Prev
    Next
    INDEX
    Explanations

    negative connotation

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

    This neuron responds to strongly negative or critical terms conveying problems, failures, mistakes, or wrongdoing.

    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
    il
    1.23
    ina
    1.15
    FR
    1.13
    ial
    1.12
    in
    1.10
    i
    1.09
    it
    1.08
    ially
    1.06
    an
    1.05
    im
    1.04
    POSITIVE LOGITS
    ग्रस्त
    1.65
     horribly
    1.33
     miserably
    1.22
    🤮
    1.20
    呻
    1.15
     Darth
    1.14
    グリップ
    1.13
    গ্রস্ত
    1.12
    )=-
    1.10
    😑
    1.09
    Activations Density 3.987%

    No Known Activations