© 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. 10893
    Prev
    Next
    INDEX
    Explanations

    created documentinserted

    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
     CDF
    0.46
     equilíbrio
    0.42
    菏
    0.42
    Semif
    0.41
    ठान
    0.41
    OpenFile
    0.40
    Cotton
    0.40
     query
    0.39
    棉
    0.39
    CDF
    0.38
    POSITIVE LOGITS
    hamming
    0.41
    ضاع
    0.40
    matched
    0.40
     MOD
    0.37
    膀
    0.37
    MOD
    0.37
    akanan
    0.37
    iberg
    0.37
    mod
    0.36
    msup
    0.36
    Activations Density 0.001%

    No Known Activations