© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93181
    Prev
    Next
    INDEX
    Explanations

    .com / .net domains

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

    This neuron responds to unusually long tokens—typically multi‐character identifiers, file or URL fragments, and other technical names.

    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
     to
    -1.38
    For
    -1.23
    To
    -1.17
    That
    -1.16
    With
    -1.13
    Those
    -1.09
    When
    -1.08
     if
    -1.02
    At
    -1.02
     those
    -1.02
    POSITIVE LOGITS
     USING
    1.22
    向けの
    1.17
     cérami
    1.10
    ISTAN
    1.06
     horrible
    1.06
     Πολ
    1.05
    のご紹介
    1.02
    kiem
    1.02
     theolog
    0.98
    GRAPHS
    0.98
    Activations Density 0.028%

    No Known Activations