© 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. 188762
    Prev
    Next
    INDEX
    Explanations

    agreeing to terms or laws

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

    things to

    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
     ساخته
    0.46
    能够在
    0.46
    ストン
    0.44
    retching
    0.44
     ī
    0.41
    peł
    0.41
    that
    0.41
     রয়ে
    0.40
    руют
    0.40
     পেয়েছেন
    0.39
    POSITIVE LOGITS
    obre
    0.45
    Aprend
    0.44
    使用
    0.43
     সুন্দরী
    0.43
     Traditional
    0.41
     BEAUT
    0.41
     refrained
    0.40
     tradicionales
    0.40
    乂
    0.40
     Dương
    0.40
    Activations Density 0.002%

    No Known Activations