© 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. 69180
    Prev
    Next
    INDEX
    Explanations

    foreign and diverse words

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

    high equity

    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
    もり
    0.46
    ală
    0.45
    埧
    0.45
    ઠી
    0.44
    一
    0.44
    キャンプ
    0.43
    陬
    0.43
    暖かい
    0.42
    従来の
    0.42
    題
    0.42
    POSITIVE LOGITS
     infinit
    0.60
     introvert
    0.57
     Ebola
    0.55
     infarct
    0.50
     verschiedenen
    0.50
    📊
    0.50
     varios
    0.49
     subtração
    0.49
     несколько
    0.49
     Hernández
    0.49
    Activations Density 0.000%

    No Known Activations