© 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. 34-GEMMASCOPE-RES-131K
    7. 118914
    Prev
    Next
    INDEX
    Explanations

    professional leagues

    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_34/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
     Behandlung
    -0.75
     čist
    -0.71
    Uwe
    -0.69
    以來
    -0.68
     见
    -0.68
    libert
    -0.68
    regierung
    -0.67
    Zie
    -0.67
    讨厌
    -0.66
    ều
    -0.66
    POSITIVE LOGITS
     league
    4.44
     League
    3.31
     leagues
    3.28
    league
    3.00
    League
    2.94
     LEAGUE
    2.63
    リーグ
    2.38
     Leagues
    2.19
     liga
    2.03
     لیگ
    2.00
    Activations Density 0.089%

    No Known Activations