© 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. 11297
    Prev
    Next
    INDEX
    Explanations

    file and directory structures

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

    The neuron fires on decimal numbers (floating‐point tokens), e.g. size‐or savings values.

    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
    spatial
    0.59
    geo
    0.56
    τσι
    0.56
    érations
    0.51
    cp
    0.51
    #{
    0.51
    Geo
    0.51
    gesamt
    0.51
     তোমরা
    0.51
     gis
    0.51
    POSITIVE LOGITS
     Markle
    0.59
     பிரச்சினை
    0.58
     dù
    0.56
     CONFIG
    0.55
     κάνει
    0.55
     IAAF
    0.55
     절
    0.55
     ঠিক
    0.54
     CHAIRMAN
    0.54
    洎
    0.54
    Activations Density 0.004%

    No Known Activations