© 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. 57709
    Prev
    Next
    INDEX
    Explanations

    accompanying materials, distributed files

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

    This neuron responds to structural or formatting tokens in code and markup (e.g. angle‐bracket tags, braces, and language keywords like “public”).

    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
    CIÓN
    -0.80
    haviours
    -0.79
    mbu
    -0.79
     колеса
    -0.78
    GGI
    -0.77
     Feed
    -0.77
    gouv
    -0.77
    Ħ
    -0.77
    club
    -0.75
    wä
    -0.75
    POSITIVE LOGITS
    umable
    0.76
     همراه
    0.71
    鄔
    0.69
    Herzlich
    0.68
     instead
    0.68
     extracted
    0.66
     extradition
    0.66
     verwe
    0.65
    ʵ
    0.65
     beziehen
    0.64
    Activations Density 0.003%

    No Known Activations