© 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. 3296
    Prev
    Next
    INDEX
    Explanations

    `using System`

    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
    ي
    0.73
    悆
    0.73
    ។
    0.71
     sorriso
    0.70
    ۔
    0.70
    ць
    0.69
    هم
    0.68
     negocio
    0.64
    ต์
    0.64
     moyens
    0.63
    POSITIVE LOGITS
    '
    0.99
    u
    0.84
    <0x80>
    0.83
    o
    0.79
    ’
    0.72
     is
    0.71
     were
    0.70
    к
    0.70
    ers
    0.68
    ’,
    0.66
    Activations Density 0.046%

    No Known Activations