© 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. 50177
    Prev
    Next
    INDEX
    Explanations

    multi-script vocabulary

    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
     تلك
    0.53
     masterpiece
    0.49
     المشروع
    0.46
     Ι
    0.43
     ڈیٹ
    0.43
    nings
    0.42
    目標
    0.42
     PHASE
    0.41
     সেই
    0.40
     Silent
    0.40
    POSITIVE LOGITS
    রু
    0.51
    اف
    0.46
    5
    0.46
     водой
    0.45
    झ
    0.44
    фи
    0.44
     воды
    0.43
     agua
    0.42
    븅
    0.42
    Ру
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.