© 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. 14009
    Prev
    Next
    INDEX
    Explanations

    code comments and copyright notices

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

    The neuron strongly responds to long runs of space characters (e.g. indentation or blank whitespace lines).

    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
     after
    -1.34
     their
    -1.29
     like
    -1.21
     on
    -1.21
     or
    -1.16
     as
    -1.12
     has
    -1.12
    錬
    -1.07
     which
    -1.05
     what
    -1.05
    POSITIVE LOGITS
    菒
    1.22
     phe
    1.19
    柔らかい
    1.17
     gekenn
    1.13
     gescha
    1.11
     suche
    1.09
     nimmer
    1.08
     heilig
    1.08
    particularly
    1.07
     لهذه
    1.07
    Activations Density 0.030%

    No Known Activations