© 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. 22926
    Prev
    Next
    INDEX
    Explanations

    specification or listing details

    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
     sólido
    0.46
    '
    0.45
    equivariant
    0.44
     ruso
    0.41
    VS
    0.41
     ہوئے
    0.41
    ί
    0.41
    tgts
    0.40
    _
    0.40
     aihe
    0.40
    POSITIVE LOGITS
     XIII
    0.50
     Urology
    0.49
     Agriculture
    0.48
    韪
    0.48
     Интер
    0.47
     Су
    0.46
     индиви
    0.46
    ホル
    0.46
    ल्लभ
    0.46
    𝙎
    0.46
    Activations Density 0.006%

    No Known Activations