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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56950
    Prev
    Next
    INDEX
    Explanations

    small businesses and utilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ！”
    0.45
     みたい
    0.43
     那麼
    0.43
    arrivalTime
    0.42
     ჩატი
    0.42
    エル
    0.41
    誰
    0.41
    𝑟
    0.41
     क्रिएट
    0.40
    𝗻
    0.40
    POSITIVE LOGITS
     photosynthetic
    0.45
     oscillations
    0.43
     tungsten
    0.43
     utilises
    0.43
     oxidation
    0.42
     mesures
    0.42
     deuterium
    0.42
     modell
    0.41
     biosynthetic
    0.41
     प्रकाशित
    0.40
    Activations Density 0.002%

    No Known Activations