© 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. 40-GEMMASCOPE-2-RES-262K
    7. 135625
    Prev
    Next
    INDEX
    Explanations

    lists of options

    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_40_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
     പക്ഷേ
    0.41
    UIntValue
    0.40
     прекрасно
    0.40
    ্লিশ
    0.39
     realises
    0.39
     나오고
    0.39
    *****",
    0.39
     ومش
    0.39
     ***
    0.39
    陕西
    0.39
    POSITIVE LOGITS
    ひ
    0.39
     diter
    0.38
    de
    0.37
    st
    0.36
    ヒ
    0.36
    pleo
    0.36
    反
    0.36
    :.
    0.35
    正
    0.35
    燃
    0.35
    Activations Density 0.001%

    No Known Activations