© 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. 178769
    Prev
    Next
    INDEX
    Explanations

    depends on, first draft, want to

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

    foreign language words and 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
    Ons
    0.46
    Hast
    0.44
    Slug
    0.43
    Culture
    0.43
    5
    0.43
    Eb
    0.43
    မှတ်
    0.43
    扩散
    0.43
    야
    0.42
    Anthrop
    0.41
    POSITIVE LOGITS
     afferma
    0.64
     公司
    0.55
     celebra
    0.54
     cargar
    0.53
     primi
    0.52
     chak
    0.52
     lavado
    0.52
     dinheiro
    0.51
     kilomet
    0.50
     perencanaan
    0.50
    Activations Density 0.000%

    No Known Activations