© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14195
    Prev
    Next
    INDEX
    Explanations

    separators and numbers

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

    The neuron is detecting hyphen (dash) characters in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Ligue
    0.82
     Ciò
    0.80
     Deadly
    0.79
     consac
    0.77
     Héctor
    0.77
    bson
    0.75
    Під
    0.74
     Electroly
    0.73
     Frü
    0.73
     Ō
    0.72
    POSITIVE LOGITS
    лары
    0.85
    ㅠ
    0.80
    WARD
    0.79
    ﻫ
    0.79
     оказалось
    0.76
    ыр
    0.75
    TeXAtom
    0.74
     (=
    0.74
     труб
    0.74
    плат
    0.73
    Activations Density 0.000%

    No Known Activations