© 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. 209668
    Prev
    Next
    INDEX
    Explanations

    UK, school, instructor, rates

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

    finland or replies

    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
    rš
    0.51
     стару
    0.48
     ))->
    0.48
     відкри
    0.47
    poco
    0.47
     controladores
    0.47
     конец
    0.46
     laurels
    0.46
     shawl
    0.46
    ょ
    0.46
    POSITIVE LOGITS
    uk
    0.53
    un
    0.46
    分的
    0.45
    是一個
    0.45
    am
    0.44
    的一個
    0.44
    ces
    0.44
    國
    0.44
     ny
    0.43
     Finland
    0.43
    Activations Density 0.001%

    No Known Activations