© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47673
    Prev
    Next
    INDEX
    Explanations

    formulas and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }]
    0.48
     eliminate
    0.46
     tt
    0.45
     additional
    0.44
     eliminating
    0.44
    ຼ
    0.44
     customize
    0.44
     accounted
    0.42
     }%
    0.42
    weiss
    0.42
    POSITIVE LOGITS
    空間
    0.49
     Antrieb
    0.45
    شار
    0.43
    謙
    0.43
     darin
    0.41
    Scape
    0.41
     tolerancia
    0.41
    <unused59>
    0.40
     stimul
    0.39
     Glückwunsch
    0.39
    Activations Density 0.001%

    No Known Activations