© 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-65K
    7. 3414
    Prev
    Next
    INDEX
    Explanations

    playoff spot and @ symbol

    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_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
    遺
    0.52
     odor
    0.47
     agitation
    0.46
    一篇
    0.45
    으로
    0.45
     написа
    0.44
     ngư
    0.44
     बलात्कार
    0.44
    ة
    0.44
    щи
    0.44
    POSITIVE LOGITS
    号
    0.50
    Quel
    0.49
     variété
    0.48
    p
    0.48
    cento
    0.48
    highlight
    0.47
     highlighted
    0.46
    ue
    0.46
    ren
    0.46
    gg
    0.46
    Activations Density 0.000%

    No Known Activations