© 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. 216904
    Prev
    Next
    INDEX
    Explanations

    balanced design or purpose

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

    uses "like" for comparison

    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
    K
    0.60
    ق
    0.59
    Q
    0.57
    Ch
    0.54
    B
    0.54
    ف
    0.53
    Y
    0.52
    os
    0.51
    A
    0.51
    _,
    0.51
    POSITIVE LOGITS
     necesarias
    0.58
     втра
    0.58
     চাষ
    0.57
     clientèle
    0.57
     bütün
    0.56
     conocimientos
    0.55
     conhecimentos
    0.53
     оставить
    0.53
    \}=\
    0.52
     uczni
    0.52
    Activations Density 0.000%

    No Known Activations