© 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. 16349
    Prev
    Next
    INDEX
    Explanations

    approximations and quantities

    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
    ר
    1.30
    V
    1.27
    ।
    1.22
    ی
    1.17
    T
    1.14
    র
    1.13
    ו
    1.12
    ד
    1.12
    ת
    1.08
    the
    1.07
    POSITIVE LOGITS
     and
    1.11
    一個
    1.05
    一些
    1.05
    كة
    0.95
    該
    0.87
    ian
    0.84
    ado
    0.84
    ção
    0.84
    icht
    0.84
    ية
    0.81
    Activations Density 0.007%

    No Known Activations