© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9597
    Prev
    Next
    INDEX
    Explanations

    chrysanthemum, Chrysler, bronchitis, tokenizer, intonation

    np_acts-logits-general · gemini-2.5-flash-lite

    names of plant species, particularly focusing on "Chrysanthemum" and botanical taxonomy.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     If
    -3.56
     It
    -2.75
    M
    -2.59
     gesamten
    -2.56
     are
    -2.56
     Even
    -2.53
     Notably
    -2.48
     различ
    -2.44
     Numerous
    -2.39
     Many
    -2.33
    POSITIVE LOGITS
    e
    3.39
    
    3.08
    ledad
    2.33
     jTextField
    2.27
    ה
    2.22
    =}
    2.19
    ingale
    2.19
     trzech
    2.17
     IBOutlet
    2.16
     BEHAVIOR
    2.16
    Activations Density 0.002%

    No Known Activations