© 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. 27439
    Prev
    Next
    INDEX
    Explanations

    highest states

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

    coding and explanations

    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
     post
    0.52
     ಸುತ್ತ
    0.50
    น
    0.47
     south
    0.46
     must
    0.44
     north
    0.44
     Post
    0.44
     southbound
    0.44
     stat
    0.44
     wandering
    0.44
    POSITIVE LOGITS
    問題を
    0.54
     सकें
    0.46
    velopper
    0.41
     estabelecer
    0.41
    ومات
    0.41
     bersih
    0.41
    櫻
    0.41
    ことです
    0.40
    潔
    0.40
     konse
    0.40
    Activations Density 0.000%

    No Known Activations