© 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. 132467
    Prev
    Next
    INDEX
    Explanations

    Winter games or archive packages

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

    knowledge limitations

    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
    তিরিক্ত
    0.52
    ת
    0.51
    at
    0.50
    tration
    0.49
    人と
    0.48
    atation
    0.48
    oretically
    0.47
     ரொம்ப
    0.46
     خیلی
    0.45
    anguage
    0.45
    POSITIVE LOGITS
     Ari
    0.46
     maneu
    0.46
    Cleanup
    0.46
     três
    0.44
     阿
    0.44
     ثلاثه
    0.43
     Segundo
    0.43
     saranam
    0.43
    茉
    0.42
    Estado
    0.42
    Activations Density 0.001%

    No Known Activations