© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77648
    Prev
    Next
    INDEX
    Explanations

    Floating-Swipe actions or menus

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

    This neuron detects occurrences of software-library or component names (e.g. class and API identifiers) in technical code or configuration text.

    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
    ρυσ
    -0.80
    файл
    -0.72
     sustained
    -0.72
     away
    -0.71
    ៧
    -0.68
    iciones
    -0.68
     Cambrian
    -0.67
    depor
    -0.67
     ESTADO
    -0.66
    miers
    -0.65
    POSITIVE LOGITS
    localScale
    0.69
     musk
    0.69
    зани
    0.67
     ob
    0.66
     Blue
    0.66
     Kingdoms
    0.65
     Mitglied
    0.65
    aten
    0.64
    largest
    0.64
    діть
    0.64
    Activations Density 0.068%

    No Known Activations