© 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. 57711
    Prev
    Next
    INDEX
    Explanations

    code structure

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

    The neuron detects unusually long runs of whitespace (large blocks of spaces or indentation).

    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
    мне
    -0.94
    $\$
    -0.85
     manuscrit
    -0.85
    ❛
    -0.84
    Davis
    -0.83
    rospy
    -0.82
     direkt
    -0.81
    เพื่อ
    -0.81
    ЖИ
    -0.80
     $[\
    -0.79
    POSITIVE LOGITS
    を活用
    0.96
     harán
    0.92
     edilir
    0.91
    所以在
    0.91
    Setiap
    0.91
    meris
    0.91
    几十
    0.88
    iments
    0.88
    了很多
    0.88
    ications
    0.88
    Activations Density 0.078%

    No Known Activations