© 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. 115869
    Prev
    Next
    INDEX
    Explanations

    Medicare for all

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

    phrases asking questions or stating conditions

    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
    JK
    0.51
    童
    0.47
    に取り組
    0.46
    高兴
    0.46
    OU
    0.46
    选用
    0.46
    平
    0.45
    打算
    0.45
    泼
    0.45
     Remembering
    0.44
    POSITIVE LOGITS
    en
    0.50
    most
    0.50
    zerel
    0.50
    vac
    0.50
    vero
    0.50
    ismo
    0.50
    sen
    0.49
    sim
    0.48
    iança
    0.48
    mere
    0.48
    Activations Density 0.000%

    No Known Activations