© 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. 127504
    Prev
    Next
    INDEX
    Explanations

    document titles and headers

    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
    ור
    0.52
    輋
    0.51
    s
    0.50
    ের
    0.49
    ો
    0.48
    ྵ
    0.48
    INS
    0.46
    ௦
    0.44
    endom
    0.43
    OP
    0.43
    POSITIVE LOGITS
     Ethyl
    0.47
     radionu
    0.47
     wreaths
    0.46
     cometido
    0.46
     carácter
    0.45
    animity
    0.45
     Grave
    0.44
     माहिती
    0.43
    基本的に
    0.43
     Сы
    0.43
    Activations Density 0.001%

    No Known Activations