© 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. 101218
    Prev
    Next
    INDEX
    Explanations

    entities on island of

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

    explaining technical contexts

    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
     době
    0.50
     excels
    0.47
     ē
    0.46
     ủng
    0.45
     Pasar
    0.44
     أمس
    0.44
     meshes
    0.43
    钱
    0.43
    薙
    0.43
     vouchers
    0.42
    POSITIVE LOGITS
    ar
    0.59
    as
    0.55
    arap
    0.54
    ur
    0.53
    ah
    0.53
    tr
    0.53
    st
    0.52
    п
    0.51
    ir
    0.50
    any
    0.50
    Activations Density 0.000%

    No Known Activations