© 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. 12462
    Prev
    Next
    INDEX
    Explanations

    leaked internal documents

    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
    ();//
    0.42
    ANDA
    0.41
    PL
    0.40
    Ь
    0.40
    เซ
    0.40
    นั้น
    0.39
    рті
    0.39
     സെ
    0.39
     [];
    0.38
    鄢
    0.38
    POSITIVE LOGITS
     deficient
    0.48
     deficiencies
    0.45
    Lago
    0.45
     Aw
    0.44
    flops
    0.44
     Hazards
    0.43
     sujet
    0.43
     достоин
    0.42
    lla
    0.42
    ⵄ
    0.42
    Activations Density 0.001%

    No Known Activations