© 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. 6836
    Prev
    Next
    INDEX
    Explanations

    is followed by list marker or symbol

    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
     également
    0.43
    ௐ
    0.39
    なし
    0.38
    circledR
    0.37
     ইউনিভার
    0.37
     setTodos
    0.36
     Esp
    0.34
    ᴸ
    0.34
     समाचार
    0.34
    新能源
    0.33
    POSITIVE LOGITS
     afore
    0.46
     appunto
    0.45
     aforementioned
    0.41
     wspom
    0.38
     mencionado
    0.35
     escolh
    0.34
     vattati
    0.33
     mentioned
    0.33
     genannten
    0.33
     doğrud
    0.33
    Activations Density 0.703%

    No Known Activations