© 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. 923
    Prev
    Next
    INDEX
    Explanations

    drug or rehabilitation center

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

    or contrasting options

    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
     klicken
    0.46
     Fernseh
    0.44
     डाउनलोड
    0.41
    plotlib
    0.41
     реєстра
    0.39
    叕
    0.39
     tableware
    0.39
    ুগত্য
    0.38
     казіно
    0.38
     Klicken
    0.38
    POSITIVE LOGITS
     [[[
    0.45
    ři
    0.41
    sa
    0.40
    if
    0.39
     πολύ
    0.39
     and
    0.39
    atrice
    0.38
    irat
    0.38
     oftentimes
    0.38
    oyen
    0.38
    Activations Density 0.005%

    No Known Activations