© 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. 106189
    Prev
    Next
    INDEX
    Explanations

    Dis Pater

    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
    saraba
    0.59
     Surprisingly
    0.55
    Filter
    0.52
     Remarkably
    0.52
    ریہ
    0.51
    눗
    0.50
    驭
    0.50
    JDK
    0.49
     Tokugawa
    0.49
    UART
    0.48
    POSITIVE LOGITS
     were
    0.80
     diese
    0.58
     waren
    0.56
     erano
    0.55
    é
    0.55
    ledo
    0.53
     twor
    0.53
     étaient
    0.52
     fueron
    0.52
     veliko
    0.51
    Activations Density 0.000%

    No Known Activations