© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58327
    Prev
    Next
    INDEX
    Explanations

    file paths

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

    The neuron fires on forward‐slash separators in version‐control diff headers, i.e. the “/” tokens that split repository or file‐system paths.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     caseros
    -1.37
    痈
    -1.36
     vinilo
    -1.35
     grün
    -1.32
     erwor
    -1.30
    を決
    -1.30
     bambú
    -1.28
    ⧼
    -1.27
    がとても
    -1.27
     grotte
    -1.24
    POSITIVE LOGITS
     članak
    1.60
     until
    1.56
     после
    1.55
     even
    1.55
     hingga
    1.45
     but
    1.41
    俢
    1.39
     for
    1.38
     nawet
    1.36
     bahkan
    1.31
    Activations Density 0.016%

    No Known Activations