© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13607
    Prev
    Next
    INDEX
    Explanations

    youtube handles and /@ urls

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

    The neuron is detecting decimal numbers (numerical tokens containing a dot).

    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
     @
    0.70
     @"
    0.67
     Rumah
    0.62
     Dylan
    0.60
     Miyazaki
    0.59
     Yang
    0.59
     Nxc
    0.58
     Dataset
    0.58
     {@
    0.57
     Yay
    0.57
    POSITIVE LOGITS
     दिमाग
    0.59
    cione
    0.58
     consultant
    0.57
    स्तिष्क
    0.56
    argeon
    0.55
    abases
    0.55
     elim
    0.54
    િસ્
    0.53
     аспек
    0.53
     சற்று
    0.52
    Activations Density 0.005%

    No Known Activations