© 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. 9352
    Prev
    Next
    INDEX
    Explanations

    making progress or related concepts

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

    The neuron fires strongly on words that denote progress or advancement (e.g., “progress,” “made,” “strides,” “overcome”).

    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
     Фер
    0.73
     FERN
    0.63
     Folklore
    0.63
     Fern
    0.61
    শে
    0.61
     Flores
    0.60
    မ္
    0.60
    𝙵
    0.59
     Forests
    0.58
     Фо
    0.58
    POSITIVE LOGITS
    ive
    0.94
    ively
    0.94
    ful
    0.91
    iveness
    0.84
    ives
    0.80
    IVE
    0.78
    sion
    0.78
    orship
    0.76
    ivamente
    0.75
    ivität
    0.73
    Activations Density 0.155%

    No Known Activations