© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11950
    Prev
    Next
    INDEX
    Explanations

    export keyword

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

    The neuron activates on terms that express reliability or guarantee aspects—especially words about availability or safety in a legal/disclaimer context.

    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_31_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
    import
    0.70
    Mixin
    0.63
    Imports
    0.59
    Cliente
    0.57
    pragma
    0.56
    Corollary
    0.56
    Влади
    0.56
    @
    0.56
    Shim
    0.55
    ,_
    0.55
    POSITIVE LOGITS
     краю
    0.61
     odmah
    0.59
     efficaces
    0.59
    orten
    0.56
     caminos
    0.56
     området
    0.56
    にとって
    0.55
     nécessaires
    0.55
     perek
    0.55
     associés
    0.55
    Activations Density 0.000%

    No Known Activations