© 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-65K
    7. 46249
    Prev
    Next
    INDEX
    Explanations

    common word sequences

    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_65k_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
    პერ
    0.49
    եր
    0.48
     नुकसान
    0.48
    芑
    0.47
     تعیین
    0.46
     था
    0.46
    ន្ថ
    0.45
     supernat
    0.45
    determination
    0.45
    स्त्रा
    0.45
    POSITIVE LOGITS
    '
    0.52
    ↵↵
    0.48
    vb
    0.46
     unfold
    0.41
     on
    0.41
     Alb
    0.41
    bij
    0.41
    resin
    0.40
     aqueous
    0.39
     infiltrate
    0.39
    Activations Density 0.010%

    No Known Activations