© 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. 205137
    Prev
    Next
    INDEX
    Explanations

    explaining functions, reverse, however, enjoying

    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
     amplifying
    0.47
    azolid
    0.44
    volver
    0.42
    千萬
    0.41
    បន្ទ
    0.41
     obliter
    0.41
     jangka
    0.41
    ✱
    0.40
     degener
    0.40
     erasing
    0.40
    POSITIVE LOGITS
     Katrina
    0.44
     Cassidy
    0.43
     Eastwood
    0.42
     Solutions
    0.41
     Ryan
    0.41
    Solutions
    0.41
    י
    0.41
     Research
    0.40
     Dickinson
    0.40
     Kayla
    0.40
    Activations Density 0.006%

    No Known Activations