© 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. 194513
    Prev
    Next
    INDEX
    Explanations

    Dragon Quest

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

    units and scientific terms

    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
    ła
    0.53
    ビス
    0.52
    arów
    0.52
    覇
    0.49
    cers
    0.47
    ニコ
    0.47
     prisms
    0.46
    леду
    0.46
    당
    0.45
    歷
    0.45
    POSITIVE LOGITS
     Alhamdulillah
    0.50
     Casey
    0.46
     Houston
    0.46
     Mifflin
    0.45
     Yangzhou
    0.44
     Huntsville
    0.44
     Clipping
    0.43
     Assistance
    0.43
     punching
    0.43
     Qualifying
    0.42
    Activations Density 0.000%

    No Known Activations