© 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. 222622
    Prev
    Next
    INDEX
    Explanations

    Flutter class names

    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
    കല
    0.41
    startswith
    0.38
     recognising
    0.38
     effectivement
    0.37
    pliance
    0.36
    absolutely
    0.35
    <0xD7>
    0.35
    Ő
    0.34
    ๔
    0.34
    Viv
    0.34
    POSITIVE LOGITS
     сту
    0.45
    ToBounds
    0.44
     Induced
    0.43
     gan
    0.41
     heaters
    0.41
     দূতাবাসের
    0.41
     casting
    0.40
     Until
    0.40
    _->
    0.39
    عکس
    0.39
    Activations Density 0.001%

    No Known Activations