© 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. 95570
    Prev
    Next
    INDEX
    Explanations

    legal appeals and petitions

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

    The neuron activates on long runs of whitespace or repeated non‐alphanumeric characters (e.g. extended space blocks or separator 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
     and
    -1.66
     four
    -1.24
     burgeoning
    -1.20
     for
    -1.16
     hombres
    -1.16
     on
    -1.15
     revital
    -1.13
     แท้
    -1.13
     srd
    -1.12
     gave
    -1.10
    POSITIVE LOGITS
     largely
    1.59
     !!!!
    1.47
     remarkably
    1.47
     ゆう
    1.34
     !!!!!
    1.27
     blatant
    1.27
     exceptionally
    1.24
     VERY
    1.20
     hugely
    1.20
     significantly
    1.19
    Activations Density 0.014%

    No Known Activations