© 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. 125671
    Prev
    Next
    INDEX
    Explanations

    to find

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

    combine, inference, development, find, flights

    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
     cunning
    0.42
     deceiving
    0.41
     =
    0.41
     haya
    0.40
    itoral
    0.40
    argu
    0.40
     NES
    0.39
     |
    0.39
     sh
    0.39
     |=
    0.38
    POSITIVE LOGITS
    鐵
    0.55
     ఫ్రె
    0.54
     Stairs
    0.54
    زة
    0.50
    Ղ
    0.49
     Nghị
    0.48
    𝘼
    0.48
     பை
    0.48
     Jehová
    0.48
     sắt
    0.47
    Activations Density 0.001%

    No Known Activations