© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 18084
    Prev
    Next
    INDEX
    Explanations

    chess notation

    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_16_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
    Enhanced
    0.59
    us
    0.54
    I
    0.52
    เร็จ
    0.50
     lear
    0.50
    rock
    0.49
     rise
    0.49
     cryst
    0.48
    OVER
    0.48
    dil
    0.48
    POSITIVE LOGITS
     Çünkü
    0.63
    무리
    0.54
     universidades
    0.54
    니까
    0.54
     Almanya
    0.54
     académ
    0.53
     Secundaria
    0.52
    प
    0.52
     Aquí
    0.51
     chiamata
    0.51
    Activations Density 0.002%

    No Known Activations