© 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. 973
    Prev
    Next
    INDEX
    Explanations

    C

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

    The main thing this neuron does is detect degree-or-quantity modifiers—words that express magnitude, intensity, or amount.

    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
    R
    0.81
    EL
    0.80
    IN
    0.76
     nedenle
    0.75
    AN
    0.74
    O
    0.73
    MEL
    0.72
    P
    0.72
    AR
    0.72
    </sup>
    0.71
    POSITIVE LOGITS
    𝗸
    0.80
    smanship
    0.75
    र्में
    0.70
    sthe
    0.70
    ය
    0.70
    𝘁
    0.70
    𝗰
    0.70
    銖
    0.69
     destinés
    0.68
    ैक
    0.67
    Activations Density 0.001%

    No Known Activations