© 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. 3860
    Prev
    Next
    INDEX
    Explanations

    accessible, suitable, extensible, viable

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

    This neuron detects evaluative or promotional language emphasizing product features or benefits.

    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
    ジー
    0.67
    ’
    0.65
     Haan
    0.64
    ور
    0.63
    frau
    0.63
     Putra
    0.61
    갓
    0.61
    だったら
    0.61
     Desar
    0.60
     mendengar
    0.60
    POSITIVE LOGITS
     easier
    0.84
     ineligible
    0.75
     an
    0.73
     möjligt
    0.71
     possible
    0.69
     diğer
    0.68
     advisable
    0.67
     a
    0.67
     unsuitable
    0.66
     easy
    0.66
    Activations Density 0.117%

    No Known Activations