© 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. 8880
    Prev
    Next
    INDEX
    Explanations

    slightly, elongated, study presentation

    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
     egress
    0.48
     구분
    0.47
    譁
    0.47
    獭
    0.45
     सहानुभूति
    0.45
     tah
    0.44
     liik
    0.44
    దాయ
    0.44
     컴퓨
    0.44
    擾
    0.43
    POSITIVE LOGITS
    ا
    0.46
    Лю
    0.45
    autos
    0.45
    robes
    0.44
     colleagues
    0.43
    oids
    0.43
    公式
    0.42
     originals
    0.41
    ipple
    0.41
    izielle
    0.41
    Activations Density 0.002%

    No Known Activations