© 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. 117456
    Prev
    Next
    INDEX
    Explanations

    discography

    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
    ки
    1.52
    is
    1.44
    an
    1.41
    ಾ
    1.38
    к
    1.37
    र
    1.36
    at
    1.20
    ر
    1.18
    т
    1.17
    ো
    1.16
    POSITIVE LOGITS
     in
    1.52
    ও
    1.28
    在
    1.17
    க்கு
    1.12
     Disc
    1.08
    0
    1.08
    Disc
    1.04
     disc
    1.03
    も
    1.02
     في
    1.00
    Activations Density 0.002%

    No Known Activations