© 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. 8791
    Prev
    Next
    INDEX
    Explanations

    what you're interested in

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

    The neuron fires on verbs and auxiliaries introducing or following “for”/“to” in constructions expressing being equipped, eligible, trained, or allowed for something.

    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
    É
    0.75
    e
    0.73
    িয়ে
    0.72
    c
    0.71
    bbero
    0.70
    ي
    0.69
    Т
    0.67
    f
    0.66
    しま
    0.66
    ện
    0.64
    POSITIVE LOGITS
     olish
    0.76
     concernant
    0.68
     astrocytes
    0.66
    regarding
    0.66
     edilmesi
    0.64
     கூறியதாவது
    0.64
     regarding
    0.63
     globalization
    0.63
     hinsichtlich
    0.63
     abstracto
    0.63
    Activations Density 0.122%

    No Known Activations