© 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. 23094
    Prev
    Next
    INDEX
    Explanations

    the only

    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
    ச்சின்ன
    0.46
    ancellation
    0.45
    !।
    0.41
    IsDir
    0.41
    一丝
    0.41
     Quỳnh
    0.41
    𝗧
    0.41
    衅
    0.40
     கெல்வின்
    0.40
    த்தட்ட
    0.40
    POSITIVE LOGITS
     путеше
    0.43
     여행
    0.39
    ip
    0.39
     খাতে
    0.37
    찰
    0.36
    eseorang
    0.36
    ujte
    0.36
     v
    0.36
     often
    0.35
    預
    0.35
    Activations Density 0.001%

    No Known Activations