© 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. 22-GEMMASCOPE-RES-131K
    7. 16219
    Prev
    Next
    INDEX
    Explanations

    or (at your option) any later version

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

    The neuron fires on the “or … any later version” style licensing clause (especially the “or (at your option) any later version”) in GNU‐style copyright headers.

    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
     konsep
    -1.16
     potensi
    -1.11
     aspek
    -1.10
     both
    -1.10
     jantung
    -1.09
    Açık
    -1.09
    FORME
    -1.05
    fleisch
    -1.04
     suéter
    -1.04
     konflikt
    -1.03
    POSITIVE LOGITS
    n
    1.08
     anklicken
    1.01
     thậm
    0.98
    ….
    0.98
     -
    0.98
    只是一
    0.97
     內
    0.96
     estrategias
    0.96
     Experten
    0.96
    In
    0.96
    Activations Density 0.008%

    No Known Activations