© 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. 144023
    Prev
    Next
    INDEX
    Explanations

    sea tac wa

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

    exclude Galpseud

    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
    kę
    0.47
    larg
    0.45
     नाक
    0.44
    ável
    0.43
    龅
    0.43
     largely
    0.42
    ίνη
    0.42
    ệnh
    0.42
    نوع
    0.41
    φέρ
    0.41
    POSITIVE LOGITS
     incontro
    0.52
     extra
    0.48
    цыя
    0.47
    規制
    0.45
     supplémentaire
    0.44
    配列
    0.44
     demonstrators
    0.44
     ugyan
    0.44
    ܐ
    0.44
    संग
    0.44
    Activations Density 0.000%

    No Known Activations