© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32917
    Prev
    Next
    INDEX
    Explanations

    value placeholders

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

    The neuron fires on numeric tokens (especially decimal‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     menggunakan
    -0.95
     regiões
    -0.90
    bouts
    -0.89
     ultimate
    -0.87
    *******
    -0.85
    thre
    -0.84
     águas
    -0.84
    ;?
    -0.84
    GROUP
    -0.84
    july
    -0.83
    POSITIVE LOGITS
    salario
    0.90
    いくつ
    0.89
     zoveel
    0.88
    Televis
    0.87
    Siapa
    0.85
     ہیں
    0.84
    Название
    0.83
     schuhe
    0.82
    Samstag
    0.82
     melap
    0.82
    Activations Density 0.001%

    No Known Activations