© 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. 138089
    Prev
    Next
    INDEX
    Explanations

    registrar, health, vehicle, chore

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

    tailored content marketing

    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
     &
    0.46
     clinics
    0.45
    .]
    0.44
     fluorescence
    0.44
    !
    0.43
    .}
    0.43
    ↵
    0.42
     tj
    0.42
     agus
    0.41
     chữa
    0.41
    POSITIVE LOGITS
    individu
    0.43
     понятие
    0.43
     мечта
    0.43
    ﺱ
    0.43
    ുവരി
    0.42
    我自己
    0.42
    箬
    0.42
    欺
    0.41
    ุย
    0.41
    дума
    0.41
    Activations Density 0.002%

    No Known Activations