© 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. 40-GEMMASCOPE-2-RES-262K
    7. 167786
    Prev
    Next
    INDEX
    Explanations

    colon, period, semicolon

    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_40_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
     тому
    0.38
     unsub
    0.38
    inen
    0.37
    ücklich
    0.37
     чув
    0.37
     unconditional
    0.37
    還
    0.37
    }`,
    0.35
    สวัสดี
    0.35
    dfe
    0.35
    POSITIVE LOGITS
    羹
    0.36
    sea
    0.35
    šo
    0.35
     मनात
    0.35
     multiplets
    0.34
    韶
    0.34
    cze
    0.34
    াপে
    0.34
    клада
    0.34
    皁
    0.34
    Activations Density 0.002%

    No Known Activations