© 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. 130785
    Prev
    Next
    INDEX
    Explanations

    essay creation needs

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

    Low FODMAP foods and carbohydrates

    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
     cipher
    0.50
    cipher
    0.50
     كلمه
    0.43
     شوي
    0.42
    ار
    0.42
    ']=$
    0.42
    ارس
    0.41
    зе
    0.41
    ОР
    0.41
    ০১
    0.41
    POSITIVE LOGITS
     Rivière
    0.49
    滏
    0.48
     presume
    0.47
     Universität
    0.46
     ahí
    0.45
     Hafen
    0.45
     Rouen
    0.44
     şey
    0.43
     impermeable
    0.43
     successivement
    0.43
    Activations Density 0.002%

    No Known Activations