© 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. 574
    Prev
    Next
    INDEX
    Explanations

    resource paths after equals

    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
     our
    -1.66
     Männern
    -1.49
     his
    -1.43
    ed
    -1.39
     what
    -1.38
    犴
    -1.36
    แรก
    -1.31
    ～　
    -1.27
     クー
    -1.27
    oubtedly
    -1.27
    POSITIVE LOGITS
    ↵↵
    1.40
     The
    1.31
    ES
    1.20
     ApJ
    1.20
    肺
    1.16
    Serie
    1.13
     '''
    1.13
     ويكيميديا
    1.13
    scrollbar
    1.13
     والث
    1.13
    Activations Density 0.027%

    No Known Activations