© 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. 6069
    Prev
    Next
    INDEX
    Explanations

    bolded introductory phrases

    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
    不僅
    0.36
    <unused467>
    0.35
    不仅
    0.35
     உள்ளிட்ட
    0.35
     सहित
    0.35
     नए
    0.34
     সেটি
    0.34
    <unused273>
    0.34
    <unused412>
    0.33
     बेहतरीन
    0.33
    POSITIVE LOGITS
     isotherms
    0.36
     anarchy
    0.33
     isotherm
    0.32
     dexterity
    0.32
     eigenvectors
    0.31
     diurnal
    0.30
     rainbows
    0.30
     troughs
    0.30
     heg
    0.29
     unitarity
    0.29
    Activations Density 0.357%

    No Known Activations