© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129238
    Prev
    Next
    INDEX
    Explanations

    English phrases and technical terms

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

    automating online processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     université
    0.51
     avaient
    0.50
     паліты
    0.50
     لقد
    0.50
    猙
    0.49
     भ्र
    0.49
     انه
    0.48
     исследования
    0.48
     अलं
    0.48
    ))&&(
    0.48
    POSITIVE LOGITS
    Json
    0.49
    Href
    0.48
    Autocomplete
    0.46
    UserName
    0.45
    更多
    0.44
    Ajax
    0.44
    Ago
    0.43
     Japan
    0.43
    日本人
    0.42
    ወስ
    0.42
    Activations Density 0.001%

    No Known Activations