© 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. 19331
    Prev
    Next
    INDEX
    Explanations

    across the spectrum

    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
    ا
    0.62
    ோவின்
    0.60
     полноцен
    0.58
    otry
    0.55
    uminação
    0.55
     இன்னொரு
    0.54
     особенности
    0.54
     específ
    0.54
    போன்ற
    0.53
    advantages
    0.53
    POSITIVE LOGITS
     across
    1.08
    across
    0.90
    Across
    0.86
     Across
    0.79
     spectrum
    0.71
    ,
    0.66
    7
    0.63
     semua
    0.59
    -
    0.57
    ㅍ
    0.56
    Activations Density 0.029%

    No Known Activations