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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 8566
    Prev
    Next
    INDEX
    Explanations

    copyright and disclaimer notices

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

    The neuron strongly fires on software‐engineering and licensing jargon (e.g. code identifiers, library names, license keywords, XML/configuration tags)—basically technical terms from code and its boilerplate.

    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
    miştir
    -0.81
     Jungfrau
    -0.81
    vsk
    -0.76
    setto
    -0.76
    ünüz
    -0.74
    ulx
    -0.73
    ichni
    -0.72
    tosa
    -0.72
    ZM
    -0.71
    (',');
    -0.71
    POSITIVE LOGITS
     Dash
    0.97
    Dash
    0.88
    冲
    0.84
     Marianne
    0.82
     juvenile
    0.73
     Elin
    0.72
    轨道
    0.72
     dash
    0.72
    Économie
    0.70
    DASH
    0.68
    Activations Density 0.040%

    No Known Activations