© 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. 10-GEMMASCOPE-RES-131K
    7. 129752
    Prev
    Next
    INDEX
    Explanations

    College, Health, VP

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

    The neuron is highly responsive to tokens that carry an unusual leading whitespace character (i.e. tokens prefixed by a non-standard space) rather than the normal space.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ꠥ
    -1.49
    com
    -1.27
                       
    -1.25
    所有
    -1.21
    에
    -1.20
    ）
    -1.20
           
    -1.20
    AS
    -1.18
    https
    -1.17
    ","
    -1.17
    POSITIVE LOGITS
     such
    2.05
     something
    1.55
     faute
    1.34
    ヤマハ
    1.26
     tehn
    1.23
     Deber
    1.23
     Seleccion
    1.21
     Ajust
    1.20
    新しく
    1.19
    learned
    1.18
    Activations Density 0.211%

    No Known Activations