© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6044
    Prev
    Next
    INDEX
    Explanations

    j increment

    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_31_width_16k_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
    fireFlower
    0.39
    2
    0.37
    foreach
    0.37
    遍历
    0.37
    ogener
    0.36
     rafters
    0.35
     Liter
    0.35
    LENGTH
    0.35
     ખૂ
    0.35
     কিন্তু
    0.34
    POSITIVE LOGITS
    他們的
    0.41
    jež
    0.39
     permanently
    0.39
     obsah
    0.39
    ಿ
    0.38
     ESPE
    0.38
     विराज
    0.37
    ப்படுத்தும்
    0.37
     beachten
    0.37
     tonight
    0.36
    Activations Density 0.207%

    No Known Activations