© 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. 241048
    Prev
    Next
    INDEX
    Explanations

    bills, Campaign, ten, marketing, law

    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
     новых
    0.49
     মোহাম্মদ
    0.48
     !,
    0.47
     '/',
    0.46
     карты
    0.46
    hamton
    0.44
    ás
    0.43
     Crear
    0.43
    ánchez
    0.43
     animación
    0.43
    POSITIVE LOGITS
    כ
    0.49
    Walmart
    0.48
    ARGS
    0.46
    Storage
    0.46
    FileDialog
    0.45
    UGG
    0.44
    ע
    0.44
    ی
    0.44
    <0xEC>
    0.44
    Atlant
    0.44
    Activations Density 0.000%

    No Known Activations