© 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. 79730
    Prev
    Next
    INDEX
    Explanations

    explaining details or examples

    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
    isation
    0.50
    íg
    0.46
    ór
    0.45
    izations
    0.45
    ización
    0.45
    परिवार
    0.45
    ఫో
    0.44
    ｛
    0.44
    ంటర్
    0.43
     ഉള്‍
    0.42
    POSITIVE LOGITS
     recess
    0.47
     বিকল্প
    0.45
     dismal
    0.43
     goof
    0.43
     comment
    0.42
     nowhere
    0.42
     cry
    0.42
     감사
    0.41
    Kind
    0.41
     declining
    0.41
    Activations Density 0.000%

    No Known Activations