© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43936
    Prev
    Next
    INDEX
    Explanations

    punishment, protection, heated, strikes, April

    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
     کوډ
    0.47
     sederhana
    0.42
     goofy
    0.42
     egyszerű
    0.41
     jendela
    0.41
    ឬ
    0.41
     Parking
    0.39
     Boeing
    0.39
    တယ်။
    0.39
    लीकरण
    0.39
    POSITIVE LOGITS
    unpublished
    0.40
    Nec
    0.39
     пен
    0.39
    ანა
    0.39
    美
    0.39
     ゙
    0.39
    Difficulty
    0.39
     mikä
    0.39
    აძ
    0.38
    ülle
    0.38
    Activations Density 0.002%

    No Known Activations