© 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. 2813
    Prev
    Next
    INDEX
    Explanations

    step-by-step reasoning

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

    This neuron fires on multiword compound expressions joined by hyphens (e.g. “one-on-one,” “end-to-end,” “side-by-side,” “hands-on”).

    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
    J
    0.93
    C
    0.87
    W
    0.81
             
    0.80
    은
    0.80
    T
    0.77
    <0x0D>
    0.74
    Three
    0.74
    6
    0.74
    B
    0.73
    POSITIVE LOGITS
     adaptability
    0.82
     φυσ
    0.82
     carelessness
    0.82
     criminality
    0.80
    𝙮
    0.80
     semantics
    0.79
     bravery
    0.79
     گئی۔
    0.79
    isesti
    0.79
     aerodynamics
    0.78
    Activations Density 0.478%

    No Known Activations