© 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. 49311
    Prev
    Next
    INDEX
    Explanations

    \

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

    multi-script characters and "echo"

    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
     polít
    0.53
    రోగ
    0.52
    ónimo
    0.52
     nombre
    0.52
     conspicuously
    0.52
     reflexión
    0.51
     sient
    0.51
     ザ
    0.50
    árs
    0.49
    ŭ
    0.49
    POSITIVE LOGITS
    ת
    0.73
    ان
    0.64
    ्ज
    0.63
    া
    0.62
    ה
    0.60
    ه
    0.59
    ਾ
    0.58
    ات
    0.57
    ed
    0.57
    ‌ای
    0.55
    Activations Density 0.008%

    No Known Activations