© 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. 71862
    Prev
    Next
    INDEX
    Explanations

    configuration file paths

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

    This neuron fires on dot‐delimited names or extensions—i.e. string literals representing file paths, URLs/domains, or other “dotted” identifiers.

    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
     could
    -1.07
    /*",
    -0.94
     Ing
    -0.94
     will
    -0.94
     had
    -0.93
     those
    -0.91
     various
    -0.91
     what
    -0.91
     low
    -0.90
     early
    -0.90
    POSITIVE LOGITS
     objectifs
    1.09
     табле
    1.04
    entrée
    0.98
     benevol
    0.98
     demandes
    0.98
    eſ
    0.96
     oes
    0.96
     nouveautés
    0.95
     取り付け
    0.94
     depic
    0.93
    Activations Density 0.044%

    No Known Activations