© 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-16K
    7. 1592
    Prev
    Next
    INDEX
    Explanations

    latitude longitude

    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_16k_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
     contemplation
    0.49
     ६
    0.46
     مغ
    0.46
     система
    0.42
    淡
    0.41
     चालू
    0.40
     UW
    0.39
     contemplate
    0.39
     mik
    0.39
     ছয়
    0.39
    POSITIVE LOGITS
    ?,
    0.52
    /,
    0.49
     खुशखबरी
    0.47
    ?(
    0.45
    érences
    0.45
    /-
    0.44
    ?.
    0.43
     ///
    0.43
    ကျင်
    0.43
    ?-
    0.42
    Activations Density 0.125%

    No Known Activations