© 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. 86777
    Prev
    Next
    INDEX
    Explanations

    blood sugar regulation & rapid effects

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

    absorption and metabolism speed

    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
     меся
    0.48
     куль
    0.46
     конденса
    0.45
     инициа
    0.44
     Deter
    0.44
    睨
    0.42
    纰
    0.41
     डिजिट
    0.41
     темно
    0.41
    誊
    0.41
    POSITIVE LOGITS
     pharmacokinetic
    0.56
     absorption
    0.54
    immediate
    0.51
    hour
    0.50
    absorption
    0.50
     rapides
    0.49
     peak
    0.49
     epinephrine
    0.49
     bioavailability
    0.48
     arousal
    0.48
    Activations Density 0.068%

    No Known Activations