© 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. 18402
    Prev
    Next
    INDEX
    Explanations

    where, use, context

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

    context of use

    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
    金額
    0.48
    ড়া
    0.46
    总
    0.45
    ფ
    0.45
    쏟
    0.44
     страте
    0.44
     мыкты
    0.43
    Ⅰ
    0.43
    總
    0.41
    ногие
    0.41
    POSITIVE LOGITS
     donde
    0.56
     uses
    0.55
     dimana
    0.55
     use
    0.54
     where
    0.52
     contextos
    0.52
     gdzie
    0.50
     herb
    0.48
     uso
    0.48
     wherein
    0.47
    Activations Density 0.035%

    No Known Activations