© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8692
    Prev
    Next
    INDEX
    Explanations

    argument, size, maxLength

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

    The neuron fires strongly on words naming violent or aggressive actions.

    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
     Klicken
    0.79
    ource
    0.73
    1
    0.73
    after
    0.72
    jectories
    0.72
    ination
    0.68
    2
    0.68
    atters
    0.67
    generated
    0.66
    नंतर
    0.66
    POSITIVE LOGITS
    літы
    0.93
     estab
    0.91
    नेटरी
    0.90
    ᒐ
    0.88
     Lanzarote
    0.86
    ўні
    0.84
     değişiklik
    0.84
     majest
    0.82
     sanctity
    0.82
     niacin
    0.82
    Activations Density 0.002%

    No Known Activations