© 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. 60651
    Prev
    Next
    INDEX
    Explanations

    two types of

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

    website and content delivery

    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
    a
    0.48
    forest
    0.47
    parentId
    0.45
    breadcrumbs
    0.44
    usual
    0.44
    access
    0.43
    MainMenu
    0.43
    mangle
    0.42
    g
    0.42
     Sheila
    0.41
    POSITIVE LOGITS
     était
    0.51
     terceiro
    0.49
     birefringence
    0.48
     étaient
    0.48
     touchscreen
    0.47
    锗
    0.47
    四年
    0.46
     olympiques
    0.45
    三年
    0.45
     monocytes
    0.45
    Activations Density 0.000%

    No Known Activations