© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 601
    Prev
    Next
    INDEX
    Explanations

    serialized version

    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_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
     your
    -1.61
     and
    -1.51
    TRIBUTES
    -1.45
    leanor
    -1.37
    artigen
    -1.36
     رابط
    -1.36
    tagHelper
    -1.34
     weakening
    -1.32
    severance
    -1.32
    ':{'
    -1.30
    POSITIVE LOGITS
    unción
    1.70
    ではまた
    1.63
    Those
    1.52
    Usually
    1.51
    ではでは
    1.47
     usually
    1.45
    ～　
    1.43
    お楽しみに
    1.38
    aconda
    1.38
    canActivate
    1.38
    Activations Density 0.084%

    No Known Activations