© 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. 22731
    Prev
    Next
    INDEX
    Explanations

    wood, vod, od, lod

    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
    চনা
    0.41
    arente
    0.39
    ಾವ್
    0.39
     incur
    0.37
    所谓
    0.37
    ść
    0.36
     Qualified
    0.36
    羡
    0.34
     Volks
    0.34
    ள
    0.34
    POSITIVE LOGITS
    yssey
    0.64
    dington
    0.50
     Под
    0.45
    ding
    0.44
    Lod
    0.42
     ўз
    0.41
    lod
    0.41
     Lod
    0.41
    וד
    0.39
     _.
    0.39
    Activations Density 0.016%

    No Known Activations