© 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. 2693
    Prev
    Next
    INDEX
    Explanations

    Names: Flora, Maya, Liam, Clara, Elara

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

    This neuron activates on proper names and named-entity titles (e.g., people’s names and place or work names).

    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
     paradoxical
    0.52
     imprecise
    0.51
     spurious
    0.50
    निष्कर्ष
    0.50
     sensit
    0.49
     HVAC
    0.49
     <*>
    0.48
     sensational
    0.47
     RDF
    0.47
    $>$
    0.47
    POSITIVE LOGITS
    ie
    0.65
    وون
    0.63
    as
    0.62
    ar
    0.61
    ah
    0.60
    z
    0.60
    ang
    0.59
    uels
    0.57
    ell
    0.56
    in
    0.56
    Activations Density 0.294%

    No Known Activations