© 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. 119747
    Prev
    Next
    INDEX
    Explanations

    send email or other data

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

    the word "send" in programming or technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    一个小
    -1.71
    ︲
    -1.49
     representado
    -1.44
     ,"
    -1.43
    
    -1.43
     других
    -1.41
    一张
    -1.41
    ':
    -1.41
     nehmen
    -1.40
     incorporado
    -1.39
    POSITIVE LOGITS
    袮
    1.90
     This
    1.84
    Their
    1.80
    They
    1.80
     Hitam
    1.65
     These
    1.63
    Despite
    1.63
     Welche
    1.59
    Although
    1.59
     Paramètres
    1.59
    Activations Density 0.000%

    No Known Activations