© 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. 33421
    Prev
    Next
    INDEX
    Explanations

    child/kids learning

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

    educational prompts and diverse languages

    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
     approximately
    0.49
     ‘
    0.43
     stupid
    0.43
     aliqu
    0.42
     unattended
    0.41
     siguientes
    0.41
     slopes
    0.41
     svg
    0.41
     Maths
    0.41
     অধিকাংশই
    0.41
    POSITIVE LOGITS
    曦
    0.46
    itative
    0.46
    赟
    0.46
    Жен
    0.45
     terwijl
    0.44
    Ін
    0.44
     díky
    0.43
     खासतौर
    0.43
    ielle
    0.43
     नती
    0.43
    Activations Density 0.005%

    No Known Activations