© 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. 38237
    Prev
    Next
    INDEX
    Explanations

    prefixes after "The"

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

    The neuron strongly activates on hexadecimal‐style byte literals (tokens like “x1F”, “xA0”, etc.).

    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
     if
    -1.52
     of
    -1.23
     Процитовано
    -1.20
     after
    -1.11
     that
    -1.07
     fjor
    -1.07
    Neben
    -1.05
    贄
    -1.05
    AfterViewInit
    -1.05
    Jeśli
    -1.05
    POSITIVE LOGITS
     cwd
    1.11
     dessas
    1.05
     desses
    1.05
     boroughs
    1.00
     CGPA
    0.99
    這些
    0.98
     these
    0.97
     bpm
    0.97
    er
    0.94
     destes
    0.94
    Activations Density 0.000%

    No Known Activations