© 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. 222158
    Prev
    Next
    INDEX
    Explanations

    screen display

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

    questionable motives or quality

    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
    وٹ
    0.51
     ตาม
    0.51
     ดวง
    0.51
     שלו
    0.50
    \!\
    0.48
    atrol
    0.48
     limite
    0.48
    𝓵
    0.47
    赜
    0.47
    श्त
    0.47
    POSITIVE LOGITS
     neoplastic
    0.48
    繚
    0.44
    洋
    0.43
     autocratic
    0.41
    ଚ
    0.40
     cod
    0.39
     encased
    0.39
     dressing
    0.38
    邪
    0.38
     hairstyles
    0.38
    Activations Density 0.001%

    No Known Activations