© 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. 184713
    Prev
    Next
    INDEX
    Explanations

    time related words or qualifiers

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

    words following "your"specialist advicemedical conditionsGerman regionsrequesting actions

    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
     Yr
    0.46
     Один
    0.45
     onwards
    0.44
     Curious
    0.43
    ப
    0.43
     औसत
    0.43
    टे
    0.42
     Vid
    0.42
    ნ
    0.42
     Curriculum
    0.41
    POSITIVE LOGITS
    iller
    0.52
     caramelized
    0.52
     卡
    0.50
    ulae
    0.47
     caramel
    0.47
    glie
    0.46
     proteína
    0.45
    ensely
    0.45
    یں۔
    0.44
     glycerin
    0.43
    Activations Density 0.001%

    No Known Activations