© 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. 148521
    Prev
    Next
    INDEX
    Explanations

    primarily supportive

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

    IIS, GPT, Sleep, Isabel

    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
    事先
    0.54
    ým
    0.51
    kým
    0.51
    耀
    0.50
    驰
    0.49
    ره
    0.48
    ر
    0.48
    éristiques
    0.48
    脾
    0.48
    rát
    0.47
    POSITIVE LOGITS
     Correctional
    0.45
     humankind
    0.45
    women
    0.43
     দেখো
    0.43
     peste
    0.43
     Illness
    0.42
     zudem
    0.41
     WOMEN
    0.41
     Women
    0.41
     seldom
    0.41
    Activations Density 0.001%

    No Known Activations