© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 33360
    Prev
    Next
    INDEX
    Explanations

    important statements

    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
    at
    0.58
    t
    0.54
    Father
    0.53
    Ste
    0.53
    p
    0.52
    n
    0.52
    ب
    0.51
    с
    0.50
    Element
    0.49
    Be
    0.48
    POSITIVE LOGITS
    ဍ
    0.47
    idam
    0.46
    )']
    0.45
    ྵ
    0.45
    hitva
    0.44
    ᱶ
    0.44
     flavors
    0.43
     flavor
    0.43
    rowser
    0.43
     mattered
    0.43
    Activations Density 0.001%

    No Known Activations