© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 13365
    Prev
    Next
    INDEX
    Explanations

    a bit of contrast or exception

    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
    ,
    0.96
     to
    0.88
    ’
    0.82
    ack
    0.64
     that
    0.59
     de
    0.59
    ы
    0.58
     at
    0.57
    urer
    0.56
     gather
    0.56
    POSITIVE LOGITS
    for
    0.91
    em
    0.85
    ু
    0.79
    ли
    0.74
    ث
    0.71
    các
    0.71
    া
    0.69
    </h2>
    0.68
    <0x0D>
    0.68
    th
    0.68
    Activations Density 0.067%

    No Known Activations