© 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. 99242
    Prev
    Next
    INDEX
    Explanations

    http or https

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

    The neuron detects long runs of whitespace (indentation) in the 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
     bailarina
    -0.82
     whim
    -0.80
    心に
    -0.79
    llavero
    -0.79
    क्षा
    -0.76
     ploy
    -0.73
    crição
    -0.72
     DIRE
    -0.71
     Advoc
    -0.71
    idend
    -0.71
    POSITIVE LOGITS
     AssemblyVersion
    0.96
    
    0.76
    masti
    0.75
    ByVersion
    0.73
    nach
    0.73
    ዣ
    0.73
    ḇ
    0.72
     こ
    0.71
     дни
    0.70
    MATCH
    0.70
    Activations Density 0.023%

    No Known Activations