© 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. 91757
    Prev
    Next
    INDEX
    Explanations

    speaker introduces categories

    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
     Нача
    0.50
    𝒚
    0.47
     超
    0.46
     一
    0.46
     一个
    0.45
     时间
    0.44
    𝑫
    0.42
     Estas
    0.42
     Во
    0.41
     superconductor
    0.41
    POSITIVE LOGITS
     диагности
    0.45
     skewers
    0.44
    ify
    0.43
     %%
    0.42
    imak
    0.41
     दिमाग
    0.41
    intestin
    0.40
     भांड
    0.40
    经销
    0.40
     diagnost
    0.39
    Activations Density 0.008%

    No Known Activations