© 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. 98926
    Prev
    Next
    INDEX
    Explanations

    foreign languages and money

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

    specific guidelines

    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
        
    0.54
     ප්‍ර
    0.50
     fastened
    0.49
     (
    0.47
    _
    0.46
     clumsy
    0.45
     Reminder
    0.44
     साक्षी
    0.44
    ánicos
    0.43
     lofty
    0.43
    POSITIVE LOGITS
     permettra
    0.50
     reçu
    0.49
    ﺨ
    0.47
    接收
    0.47
    செல்
    0.47
     imagenes
    0.47
     personnes
    0.46
     receb
    0.46
    Philippe
    0.46
     recibió
    0.45
    Activations Density 0.000%

    No Known Activations