© 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. 123334
    Prev
    Next
    INDEX
    Explanations

    gives

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

    specific word pairings

    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
     сила
    0.52
     reden
    0.50
    友
    0.46
    ての
    0.46
    t
    0.45
     drog
    0.44
     nuevos
    0.44
    endedor
    0.44
     رباع
    0.43
    ット
    0.43
    POSITIVE LOGITS
     Whirl
    0.47
     Ants
    0.47
    για
    0.46
     เฉล
    0.46
    য়ান
    0.45
     SearchView
    0.44
     Organisations
    0.44
    ব্লিউ
    0.44
    گیر
    0.44
    ن
    0.44
    Activations Density 0.001%

    No Known Activations