© 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-262K
    7. 55195
    Prev
    Next
    INDEX
    Explanations

    Pyro stares

    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_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
    繋がり
    0.42
    চ্ছিন্ন
    0.42
    elizmente
    0.41
    𝐓
    0.41
     functionality
    0.41
     funcionalidades
    0.41
     connectivity
    0.40
    {}'.
    0.40
     signaler
    0.39
     `<
    0.39
    POSITIVE LOGITS
     fácil
    0.49
     Soviet
    0.47
     every
    0.47
    无论
    0.46
     easy
    0.42
     모든
    0.42
     everywhere
    0.41
     mọi
    0.41
     łat
    0.41
    \!
    0.41
    Activations Density 0.009%

    No Known Activations