© 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. 16-GEMMASCOPE-2-RES-262K
    7. 117636
    Prev
    Next
    INDEX
    Explanations

    Debian package management

    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
    เป็นการ
    0.71
    า
    0.70
    li
    0.68
    ebabkan
    0.67
    aksana
    0.67
    ampaikan
    0.67
     kerusakan
    0.67
     असू
    0.67
    ta
    0.66
     was
    0.65
    POSITIVE LOGITS
    ك
    0.72
     enorme
    0.68
    ِّف
    0.66
     turno
    0.65
    ప
    0.64
    ي
    0.64
     manoeuvre
    0.62
    ম
    0.62
    C
    0.60
    新型
    0.60
    Activations Density 0.003%

    No Known Activations