© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52217
    Prev
    Next
    INDEX
    Explanations

    healthcare, chapter, practicing, curves

    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
     SELECTED
    0.48
    να
    0.41
    权限
    0.41
    >′</
    0.41
     vocês
    0.40
     nossa
    0.40
    ну
    0.40
    เรา
    0.39
     COMMON
    0.39
     OUR
    0.39
    POSITIVE LOGITS
    irse
    0.49
    prueba
    0.47
    informat
    0.46
    Tiempo
    0.46
     מב
    0.45
    uo
    0.43
    balanced
    0.43
    war
    0.43
    S
    0.43
    ewalk
    0.42
    Activations Density 0.009%

    No Known Activations