© 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. 40-GEMMASCOPE-2-RES-262K
    7. 98692
    Prev
    Next
    INDEX
    Explanations

    legal nuance, frosted glass

    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_40_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
    ';",
    0.41
    ইস
    0.40
     சிங்க
    0.39
     sing
    0.38
    рино
    0.38
    كلة
    0.38
    邝
    0.38
     dara
    0.37
    たん
    0.36
    üğü
    0.36
    POSITIVE LOGITS
    毫米
    0.42
     pelatihan
    0.39
    Mm
    0.38
     Meteorology
    0.38
    险
    0.37
     Petersburg
    0.36
     paradigma
    0.36
    Петербург
    0.36
    DateFormat
    0.36
     dentro
    0.35
    Activations Density 0.001%

    No Known Activations