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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33925
    Prev
    Next
    INDEX
    Explanations

    Friendly FIFA World Cup

    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
     both
    -1.48
     or
    -1.25
     whose
    -1.23
    Both
    -1.17
     new
    -1.10
    forhold
    -1.07
    because
    -1.05
     allerede
    -1.05
     chré
    -1.05
     using
    -1.04
    POSITIVE LOGITS
    偶尔
    1.13
     overal
    1.10
    Aktuelle
    1.04
    近期
    1.04
    ᡵ
    1.03
     comunicare
    1.02
    然後
    1.01
     acquistare
    0.99
    łod
    0.98
    パン
    0.97
    Activations Density 0.001%

    No Known Activations