© 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-65K
    7. 15922
    Prev
    Next
    INDEX
    Explanations

    description, version, author

    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_65k_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
    鐪
    0.44
    殮
    0.41
    abla
    0.39
     rangka
    0.39
    一时
    0.39
    ]]:
    0.38
     XXII
    0.38
    Cross
    0.38
     kart
    0.38
     depicting
    0.36
    POSITIVE LOGITS
    seqNum
    0.43
     făcut
    0.43
    rapid
    0.43
     بسرعة
    0.43
    哌
    0.43
    boek
    0.42
     humedad
    0.41
     ජ
    0.40
    钩
    0.40
    桑
    0.40
    Activations Density 0.002%

    No Known Activations