© 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. 54335
    Prev
    Next
    INDEX
    Explanations

    studio and creative work

    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
    гая
    0.53
     }.
    0.50
    ス
    0.48
    がん
    0.47
    س
    0.47
     نقط
    0.47
     أَ
    0.47
     машинасы
    0.46
    aturamento
    0.46
    cks
    0.46
    POSITIVE LOGITS
    l
    0.49
     Photography
    0.45
     법칙
    0.44
    กฏ
    0.42
     Spur
    0.41
     अफगानिस्तान
    0.41
    กฎ
    0.41
    튠
    0.41
     जहां
    0.40
    ੍ਰ
    0.40
    Activations Density 0.001%

    No Known Activations