© 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. 40263
    Prev
    Next
    INDEX
    Explanations

    unpublished unfinished essays autobiographies

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

    unpublished and unfinished works

    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
     ಜನರು
    0.52
    ຸ
    0.47
    聳
    0.47
    ディー
    0.46
     outperformed
    0.46
     незале
    0.45
    য়ং
    0.44
    される
    0.44
    ル
    0.44
     वैध
    0.44
    POSITIVE LOGITS
     unpublished
    0.69
     unfinished
    0.58
     Unpublished
    0.57
    unpublished
    0.57
     inéd
    0.56
     essay
    0.56
     revis
    0.56
     essays
    0.55
     sketches
    0.55
     autobi
    0.55
    Activations Density 0.093%

    No Known Activations