© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91107
    Prev
    Next
    INDEX
    Explanations

    URL, filenames, appeals, denied decisions

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

    The neuron fires on code identifiers related to URLs (e.g. “URL,” “NSURL,” “WithString,” “Request”) and similar technical tokens.

    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
    Carol
    -0.73
    åt
    -0.71
    remp
    -0.69
     Zep
    -0.67
     Auer
    -0.67
    ätter
    -0.66
    Bloomberg
    -0.66
    lustre
    -0.65
    ジョー
    -0.65
    멈
    -0.64
    POSITIVE LOGITS
    haraan
    0.74
    EOR
    0.71
     Krank
    0.68
     Cycling
    0.66
    cia
    0.66
    neid
    0.65
    밭
    0.63
    隄
    0.63
    velg
    0.63
     đào
    0.63
    Activations Density 0.063%

    No Known Activations