© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65876
    Prev
    Next
    INDEX
    Explanations

    unless

    np_acts-logits-general · gemini-2.5-flash-lite

    Lionel Messi's World Cup title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    噉
    0.44
     Neurosci
    0.43
     ایکسپریس
    0.43
    inus
    0.43
    不出
    0.42
    aksan
    0.41
    akaranam
    0.41
    าน
    0.40
    Reasons
    0.39
    ']);
    0.39
    POSITIVE LOGITS
    ជាមួយនឹង
    0.56
     ವೇ
    0.47
     recorrido
    0.47
     சிறந்த
    0.44
    ជាមួយ
    0.44
     करिए
    0.44
    rieg
    0.44
     ס
    0.44
    Թ
    0.43
     עם
    0.43
    Activations Density 0.000%

    No Known Activations