© 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. 177990
    Prev
    Next
    INDEX
    Explanations

    words like "thy" or "now"

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

    taking back control

    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
    Hej
    0.46
    ruf
    0.43
    ript
    0.42
     warranty
    0.42
     takePhotoButton
    0.42
     뒤
    0.41
     일으
    0.41
     예측
    0.41
     warranties
    0.41
     characterizes
    0.40
    POSITIVE LOGITS
    чка
    0.49
     патри
    0.47
    cailles
    0.45
    чке
    0.45
     inhabited
    0.45
    اريخ
    0.44
    قة
    0.44
    ಹಾಸ
    0.44
     கேட்டு
    0.43
    عادة
    0.43
    Activations Density 0.002%

    No Known Activations