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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11331
    Prev
    Next
    INDEX
    Explanations

    emulating, networked filtering, tachyonic

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ֶּ
    -1.39
    有一定
    -1.25
    出来ました
    -1.23
    ִּ
    -1.21
    Ekster
    -1.21
    狁
    -1.20
    webElement
    -1.20
     Muñoz
    -1.19
    ּוֹ
    -1.19
    当然是
    -1.17
    POSITIVE LOGITS
     掃除
    1.47
     we
    1.38
     właśnie
    1.34
     atque
    1.27
    bagai
    1.25
     inapropiados
    1.23
     which
    1.23
    områ
    1.16
     via
    1.16
     into
    1.15
    Activations Density 0.010%

    No Known Activations