© 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. 3578
    Prev
    Next
    INDEX
    Explanations

    description of physical objects

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

    The neuron responds strongly to uncommon or unusually specific content words (especially proper names and other low‐frequency tokens).

    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
    aratus
    0.79
    𝑓
    0.78
     gravitate
    0.71
     substantive
    0.70
     cumbersome
    0.70
     geométricas
    0.70
     pivoting
    0.70
     fermions
    0.68
     ferrite
    0.68
     закін
    0.68
    POSITIVE LOGITS
    א
    0.91
    Н
    0.80
    ﻘ
    0.79
    А
    0.77
     오늘의
    0.76
     vå
    0.75
    ﺪ
    0.74
     zio
    0.73
    t
    0.73
    כ
    0.73
    Activations Density 0.001%

    No Known Activations