© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91362
    Prev
    Next
    INDEX
    Explanations

    voltage readings

    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
     ഉണ്ട്
    0.43
     ies
    0.40
    的位置
    0.40
     récente
    0.39
    <0xE2>
    0.39
    example
    0.39
     hưởng
    0.39
    5
    0.38
     hibernate
    0.38
    TextInput
    0.38
    POSITIVE LOGITS
     друз
    0.50
    ด์
    0.45
     туристи
    0.43
     compagnie
    0.43
    чие
    0.42
     desolate
    0.42
     বন্ধুদের
    0.41
    逶
    0.41
    ভালো
    0.41
     gemidd
    0.41
    Activations Density 0.037%

    No Known Activations