© 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. 34-GEMMASCOPE-RES-131K
    7. 3512
    Prev
    Next
    INDEX
    Explanations

    unsafe pointers

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

    The neuron is strongly triggered by occurrences of the token “unsafe” (i.e. imports or uses of the unsafe package).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    phyllum
    -0.74
    vokat
    -0.69
    balt
    -0.68
     Policies
    -0.68
     решения
    -0.67
     arreglos
    -0.66
    importe
    -0.65
     Fuerzas
    -0.65
    otter
    -0.65
    继承
    -0.64
    POSITIVE LOGITS
    oris
    0.74
    ->__
    0.73
     Meli
    0.71
     restau
    0.67
    量子
    0.66
    Maggie
    0.66
    iration
    0.66
     Agnew
    0.65
     págs
    0.64
     WebApplication
    0.63
    Activations Density 0.037%

    No Known Activations