© 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. 21647
    Prev
    Next
    INDEX
    Explanations

    generating different text formats

    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
     inadvertently
    0.48
     ancillary
    0.48
    부
    0.46
    ologous
    0.46
     locus
    0.44
     extremes
    0.44
    付属
    0.43
    パ
    0.43
    ¿
    0.43
     sanctions
    0.42
    POSITIVE LOGITS
     Με
    0.52
    𝘮
    0.51
     乳
    0.50
    ziła
    0.50
     सफल
    0.50
    ㄗ
    0.48
     schreibt
    0.47
     实现
    0.47
     रखता
    0.47
    𝘳
    0.47
    Activations Density 0.001%

    No Known Activations