© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 76345
    Prev
    Next
    INDEX
    Explanations

    generating, creating, managing

    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
     relativistic
    0.58
    Sum
    0.51
     능
    0.50
    ଵ
    0.49
     патри
    0.47
     եւ
    0.46
    ቑ
    0.46
     й
    0.44
    젯
    0.44
    relativistic
    0.44
    POSITIVE LOGITS
     Choisissez
    0.44
    Chois
    0.42
     choisir
    0.42
     meeste
    0.41
     Có
    0.39
     beginner
    0.39
     healthcare
    0.39
     Verenigde
    0.38
     neckline
    0.38
     Miss
    0.38
    Activations Density 0.007%

    No Known Activations