© 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. 90261
    Prev
    Next
    INDEX
    Explanations

    videos and keyframes

    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
     pamoja
    0.50
     decad
    0.50
     dugo
    0.48
     तैयार
    0.47
    France
    0.47
    𝚁
    0.46
    га
    0.46
    𝚄
    0.45
     gobl
    0.45
     эле
    0.45
    POSITIVE LOGITS
     Некоторые
    0.47
    会有
    0.45
    很简单
    0.42
    但是
    0.41
    য়
    0.41
     Keyword
    0.41
     BrowserRouter
    0.40
     Scattering
    0.40
    য়
    0.40
     Canyon
    0.40
    Activations Density 0.003%

    No Known Activations