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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10814
    Prev
    Next
    INDEX
    Explanations

    Botox, masturbation, MySql, TypeId, TryParse

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

    the word "TypeId" in code and technical documentation.

    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
    e
    -3.64
    or
    -3.09
    not
    -3.05
    m
    -2.98
    man
    -2.94
    <i>
    -2.81
    when
    -2.61
    t
    -2.55
    for
    -2.52
     «
    -2.48
    POSITIVE LOGITS
    棡
    2.89
    
    2.77
    Fär
    2.66
    𔘓
    2.61
    𝔈
    2.56
    謦
    2.53
    𓆸
    2.53
    を行う
    2.53
    
    2.50
    を行い
    2.48
    Activations Density 0.002%

    No Known Activations