© 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. 89865
    Prev
    Next
    INDEX
    Explanations

    license terms or legal document sections

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

    The neuron fires strongly on metadata and code‐like identifiers—e.g. HTML/CSS tag names, attribute names, and property values.

    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
     SM
    -0.76
    laz
    -0.70
     Laz
    -0.69
     BZ
    -0.68
     Tick
    -0.68
    ccd
    -0.66
    Laz
    -0.66
     znaleźć
    -0.65
    łuż
    -0.65
     SAW
    -0.64
    POSITIVE LOGITS
    预约
    0.64
    EDS
    0.61
    cett
    0.61
    閉店
    0.61
     потреби
    0.60
     Highway
    0.60
    holdt
    0.60
     Aufführung
    0.60
    FileUtil
    0.60
    っぱい
    0.60
    Activations Density 0.068%

    No Known Activations