© 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. 227052
    Prev
    Next
    INDEX
    Explanations

    foreign language and cultural terms

    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
    “
    0.47
     select
    0.44
     optically
    0.41
     us
    0.41
     u
    0.40
    ”
    0.40
     mirror
    0.39
    向き
    0.38
    orgen
    0.38
    iels
    0.38
    POSITIVE LOGITS
     dilwale
    0.64
     מספר
    0.55
    ㍍
    0.54
     meriye
    0.52
    Marne
    0.51
     administrativas
    0.50
    mehndi
    0.50
     gacch
    0.50
    晉
    0.50
    whose
    0.49
    Activations Density 0.000%

    No Known Activations