© 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-65K
    7. 45238
    Prev
    Next
    INDEX
    Explanations

    cautions and descriptions

    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
    üks
    0.50
     サ
    0.45
    꾀
    0.44
    تبع
    0.44
     recklessly
    0.43
    痴
    0.43
    腮
    0.43
    şı
    0.43
     रात्रि
    0.42
     विशेष
    0.42
    POSITIVE LOGITS
     ficou
    0.48
     noirâtres
    0.46
    etar
    0.44
    ยืน
    0.44
    𝓭
    0.43
     nasz
    0.42
    鑾
    0.42
     advise
    0.41
    ]]]
    0.41
    鍵
    0.41
    Activations Density 0.006%

    No Known Activations