© 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. 31-GEMMASCOPE-2-RES-262K
    7. 19584
    Prev
    Next
    INDEX
    Explanations

    docstring @param, @return

    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_31_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
    вя
    0.41
    併
    0.40
     製
    0.39
    瓈
    0.38
     പ്രേ
    0.37
     Arrow
    0.37
     herbicide
    0.37
     végétaux
    0.37
    َح
    0.36
     प्रेर
    0.36
    POSITIVE LOGITS
    または
    0.38
    edLeft
    0.38
    ଛି
    0.38
    mDatas
    0.37
    を使
    0.37
    bool
    0.37
     ór
    0.37
     izme
    0.36
     exons
    0.36
    ”，“
    0.36
    Activations Density 0.002%

    No Known Activations