© 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. 34825
    Prev
    Next
    INDEX
    Explanations

    goods and basic concepts

    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
    ==========
    0.40
    debug
    0.39
    ogs
    0.38
    ==============
    0.38
    Debug
    0.38
    ----------
    0.38
    persist
    0.38
    alta
    0.37
    |_{
    0.37
    base
    0.37
    POSITIVE LOGITS
     halfway
    0.50
     midway
    0.46
     paintbrush
    0.44
     Midway
    0.43
     cityscape
    0.41
     then
    0.39
     trà
    0.39
     phones
    0.38
     :"
    0.38
     sayılı
    0.38
    Activations Density 0.000%

    No Known Activations