© 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. 7208
    Prev
    Next
    INDEX
    Explanations

    years. AD

    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
     faço
    0.37
     ইত্যা
    0.36
     manhã
    0.36
     systèmes
    0.35
    েন্টস
    0.34
     idiots
    0.34
     dónde
    0.34
     (%)
    0.34
     గారి
    0.34
    ?”,
    0.34
    POSITIVE LOGITS
    .
    0.50
    。
    0.49
    ។
    0.41
    ).
    0.40
    .)
    0.38
    ​.
    0.36
    sponsored
    0.36
     ซึ่ง
    0.35
    said
    0.35
    .(
    0.35
    Activations Density 0.052%

    No Known Activations