© 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. 10-GEMMASCOPE-RES-131K
    7. 83943
    Prev
    Next
    INDEX
    Explanations

    char arrays in code

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

    The neuron fires on array‐type mentions, especially on square‐bracket “[]” array declarations.

    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
    ↵
    -2.08
     Anſ
    -1.77
     fantasmas
    -1.68
    ⢇
    -1.64
     espectadores
    -1.63
     Türkçe
    -1.62
    螓
    -1.61
     berdua
    -1.59
     demonios
    -1.59
     was
    -1.58
    POSITIVE LOGITS
     is
    2.11
    0
    2.06
     the
    1.70
    }
    1.67
     вспом
    1.64
     spilt
    1.59
    sonaro
    1.58
    ⧼
    1.56
    3
    1.55
    犄
    1.54
    Activations Density 0.031%

    No Known Activations