© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 236570
    Prev
    Next
    INDEX
    Explanations

    semi- prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MANAGER
    0.54
    回目の
    0.52
    マ
    0.51
     SEQUENCE
    0.50
    밂
    0.49
     BOC
    0.48
    endance
    0.48
    p
    0.47
    구요
    0.47
    %；
    0.47
    POSITIVE LOGITS
    Semi
    1.12
     semi
    1.11
     Semi
    1.09
     semia
    0.98
    semi
    0.98
     semif
    0.91
     полуо
    0.86
     semic
    0.83
     sem
    0.79
     полу
    0.75
    Activations Density 0.028%

    No Known Activations