© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 195360
    Prev
    Next
    INDEX
    Explanations

    noun followed by descriptive word

    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
     arrond
    0.40
     Telef
    0.40
     prefabricated
    0.39
    箇
    0.39
     interloc
    0.39
    რძ
    0.39
    运转
    0.38
     resembles
    0.37
     myWeb
    0.37
     орга
    0.37
    POSITIVE LOGITS
     químico
    0.40
    濺
    0.40
    اء
    0.40
    សុ
    0.39
    radial
    0.39
    medal
    0.39
    Gender
    0.38
    RIBE
    0.38
    وبی
    0.38
     ಪದ
    0.38
    Activations Density 0.001%

    No Known Activations