© 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. 81399
    Prev
    Next
    INDEX
    Explanations

    Okay, this is

    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
    nos
    0.38
    l
    0.38
    geon
    0.38
    راك
    0.36
    ts
    0.36
     rhomb
    0.36
     td
    0.35
    门口
    0.35
     ellipt
    0.35
    ube
    0.35
    POSITIVE LOGITS
    </blockquote>
    0.52
     Difference
    0.43
     まま
    0.42
     Resort
    0.40
    ⠛
    0.40
     Replace
    0.39
     Konzept
    0.39
     ചെയ്യ
    0.39
     discour
    0.39
     দিলাম
    0.38
    Activations Density 0.006%

    No Known Activations