© 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. 80515
    Prev
    Next
    INDEX
    Explanations

    language identification

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

    June yoga class

    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
    りと
    0.45
     tekst
    0.44
    \%),
    0.44
     olnud
    0.43
    묭
    0.43
    ትር
    0.43
    Ты
    0.43
    ดี
    0.42
    Lt
    0.42
    𝚅
    0.42
    POSITIVE LOGITS
     देशों
    0.49
     খ্যাতি
    0.48
     ભારત
    0.46
     চীন
    0.46
    هاي
    0.46
     આવી
    0.45
     আফ্রিকার
    0.45
     പറയാ
    0.45
     চায়
    0.44
    過的
    0.43
    Activations Density 0.000%

    No Known Activations