© 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. 160853
    Prev
    Next
    INDEX
    Explanations

    proposal, businesses, permission

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

    remake surpass, photos

    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
    简直
    0.42
    син
    0.42
    ]
    0.42
     Тут
    0.41
     wiki
    0.40
     видите
    0.40
     принци
    0.39
    .[
    0.39
     ^
    0.38
     ممكن
    0.38
    POSITIVE LOGITS
    闿
    0.47
     अथवा
    0.43
     Cannabis
    0.43
    骁
    0.42
     paisajes
    0.41
    ồ
    0.41
    campfire
    0.41
    ő
    0.40
     Canadiens
    0.40
    èt
    0.40
    Activations Density 0.000%

    No Known Activations