© 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. 174512
    Prev
    Next
    INDEX
    Explanations

    foreign words and entities

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

    foreign text/phrases

    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
    feast
    0.50
    french
    0.50
    import
    0.48
    tik
    0.48
    vista
    0.48
    路
    0.48
    kis
    0.47
    haha
    0.46
    hore
    0.46
    european
    0.46
    POSITIVE LOGITS
     unbedingt
    0.55
    Ơ
    0.48
     Jeder
    0.46
     עבור
    0.45
    לו
    0.44
     Dieser
    0.44
     Medell
    0.42
     Kohler
    0.42
     Männer
    0.42
     Laravel
    0.42
    Activations Density 0.000%

    No Known Activations