© 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-16K
    7. 7701
    Prev
    Next
    INDEX
    Explanations

    optional and extra

    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_16k_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
    Fecha
    0.47
    ഌ
    0.43
     परख
    0.42
    レクトリ
    0.42
    <0x8F>
    0.42
     Kaur
    0.41
    Kom
    0.41
    谣
    0.41
     naman
    0.40
    Alla
    0.40
    POSITIVE LOGITS
    额外的
    1.21
     дополнительных
    1.16
     additional
    1.15
     zusätzlichen
    1.14
     дополни
    1.11
     supplementary
    1.11
     дополнительные
    1.11
     Additional
    1.09
    追加
    1.09
     supplement
    1.08
    Activations Density 0.639%

    No Known Activations