© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11651
    Prev
    Next
    INDEX
    Explanations

    fonts, omitting, inconsistent

    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
     ĝi
    0.59
    了起来
    0.53
    起来
    0.50
     proyecto
    0.45
    Codec
    0.45
     එය
    0.43
    它
    0.43
     đã
    0.42
    ModelAndView
    0.42
    Project
    0.42
    POSITIVE LOGITS
     fonts
    0.53
     omitting
    0.53
     шрифт
    0.52
     inconsistent
    0.50
     некоторым
    0.46
     некоторые
    0.46
     certaines
    0.45
     niektó
    0.45
     шриф
    0.45
    வுகளில்
    0.44
    Activations Density 0.082%

    No Known Activations