© 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. 15435
    Prev
    Next
    INDEX
    Explanations

    company events, storytelling elements, coding terms

    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
    비
    0.69
    2
    0.62
    자
    0.57
    새
    0.56
    Ꮁ
    0.53
    ADER
    0.52
    수
    0.52
    ח
    0.52
    치
    0.51
    려
    0.51
    POSITIVE LOGITS
     maupun
    0.63
     dengan
    0.63
     trong
    0.63
     atau
    0.62
     dihar
    0.62
    મિંગ
    0.60
     destiné
    0.59
     στην
    0.59
     หรือ
    0.59
     yoki
    0.59
    Activations Density 0.062%

    No Known Activations