© 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. 22-GEMMASCOPE-RES-131K
    7. 39015
    Prev
    Next
    INDEX
    Explanations

    dimensions and specifications

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

    This neuron appears to be effectively inactive—it does not reliably detect or respond to any specific token or pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     when
    -1.24
     that
    -1.22
     Ajoutez
    -1.00
     gelangt
    -0.99
    dich
    -0.97
     whose
    -0.97
     what
    -0.94
    ㈱
    -0.94
    كة
    -0.94
     contribution
    -0.92
    POSITIVE LOGITS
    Handlung
    1.12
    tigheter
    1.05
    ruptcy
    1.02
    ське
    1.00
    ął
    0.99
    zą
    0.99
    brokes
    0.98
    𞤢
    0.98
     astonishing
    0.97
     печени
    0.96
    Activations Density 0.001%

    No Known Activations