© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54760
    Prev
    Next
    INDEX
    Explanations

    technical or financial terms

    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
     Painlev
    0.46
     என்பதை
    0.46
     nDims
    0.44
     embell
    0.42
     abruptly
    0.41
     plufieurs
    0.41
     ['
    0.40
     discontinuities
    0.39
     instabilities
    0.39
     updateTotal
    0.39
    POSITIVE LOGITS
     ample
    0.41
    ဝန်
    0.39
    =
    0.38
     agreed
    0.37
    get
    0.37
     hơi
    0.36
    yin
    0.36
    PH
    0.36
     tý
    0.36
     तस्वीरें
    0.36
    Activations Density 0.020%

    No Known Activations