© 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. 30855
    Prev
    Next
    INDEX
    Explanations

    authenticity, Turk, descendants

    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
    盼
    0.48
    νη
    0.46
     triumph
    0.45
    رة
    0.45
     файлы
    0.44
    煊
    0.44
     alimento
    0.41
     infek
    0.41
    还得
    0.41
     vä
    0.41
    POSITIVE LOGITS
    atch
    0.46
    ček
    0.45
     LEVELS
    0.45
    लोड
    0.44
    0
    0.44
    寛
    0.44
    Շ
    0.42
    pesar
    0.41
    shirt
    0.41
     camisa
    0.40
    Activations Density 0.008%

    No Known Activations