© 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. 208343
    Prev
    Next
    INDEX
    Explanations

    selling autographs, legal standing, Invoice

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

    Gemma API or App

    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
    日语
    0.51
    онер
    0.44
    ﱢ
    0.44
    在日本
    0.43
     consentement
    0.42
    WRITE
    0.42
    FREQUENCY
    0.42
    aprendizaje
    0.41
    믿
    0.41
    ىر
    0.41
    POSITIVE LOGITS
     towards
    0.53
    𝓭
    0.53
    akkhan
    0.50
     Juniper
    0.48
    한
    0.48
    टान
    0.47
    貅
    0.46
     กัน
    0.45
     Invoice
    0.45
    Фа
    0.45
    Activations Density 0.000%

    No Known Activations