© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78233
    Prev
    Next
    INDEX
    Explanations

    Záhony, Part

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

    The neuron flags sections of source code—especially C-style comment blocks and code-like constructs.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     judi
    -0.84
     vettor
    -0.84
     cabine
    -0.82
     trase
    -0.75
     believing
    -0.75
     PAGER
    -0.74
     STEEL
    -0.73
    採用
    -0.73
     PINE
    -0.72
     creer
    -0.71
    POSITIVE LOGITS
     النبات
    0.84
    nj
    0.79
    zeniem
    0.78
     vuonna
    0.77
     especie
    0.77
     espèce
    0.76
    sst
    0.76
     joka
    0.75
     kész
    0.75
    Mö
    0.74
    Activations Density 0.011%

    No Known Activations