© 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. 6845
    Prev
    Next
    INDEX
    Explanations

    immediate action

    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
    older
    0.50
    ust
    0.47
    onn
    0.44
    1
    0.44
    ot
    0.44
    uw
    0.43
    mars
    0.43
    yn
    0.43
     norske
    0.43
    vus
    0.42
    POSITIVE LOGITS
     пище
    0.51
     Environment
    0.49
    Дру
    0.47
     оптими
    0.46
     aang
    0.46
    Verified
    0.46
     فريبي
    0.46
     ગો
    0.46
    앵
    0.45
    pleClass
    0.45
    Activations Density 0.008%

    No Known Activations