© 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. 39403
    Prev
    Next
    INDEX
    Explanations

    sc followed by (

    np_acts-logits-general · gemini-2.5-flash-lite

    measuring specific factors

    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
    да
    0.57
    Б
    0.57
    на
    0.54
    ETER
    0.51
    como
    0.51
    ДА
    0.50
    倶
    0.50
    Ти
    0.49
    edil
    0.49
    Doctors
    0.48
    POSITIVE LOGITS
    先前
    0.45
     før
    0.45
     Sikkim
    0.45
     entrepreneurs
    0.43
     sebelum
    0.43
     trước
    0.41
     ingin
    0.41
     BEFORE
    0.41
     Sở
    0.40
     retails
    0.40
    Activations Density 0.000%

    No Known Activations