© 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. 247325
    Prev
    Next
    INDEX
    Explanations

    shall mean, links, mission, however, crack

    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
    辮
    0.47
    兒子
    0.46
    வருக்கும்
    0.45
    蛋白質
    0.45
    及び
    0.45
     জাহান
    0.44
    jectory
    0.43
     að
    0.43
    訊
    0.43
    が可能
    0.43
    POSITIVE LOGITS
    lact
    0.48
     каль
    0.47
    aqua
    0.46
     AMA
    0.46
    teria
    0.45
     pure
    0.45
    ка
    0.44
    IZA
    0.44
     diaper
    0.44
    gsm
    0.44
    Activations Density 0.000%

    No Known Activations