© 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. 32764
    Prev
    Next
    INDEX
    Explanations

    which

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

    context for analysis

    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
    न
    0.63
    ن
    0.57
    ให้กับ
    0.52
    那里
    0.50
    น
    0.50
    ként
    0.49
     teníamos
    0.49
    า
    0.49
    ร์
    0.49
    ums
    0.47
    POSITIVE LOGITS
    soever
    0.57
    তে
    0.53
     ஈடுப
    0.52
    並不
    0.52
     an
    0.51
     resten
    0.51
    subTest
    0.50
     arbeiten
    0.50
    توى
    0.50
     pouze
    0.49
    Activations Density 0.062%

    No Known Activations