© 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. 193946
    Prev
    Next
    INDEX
    Explanations

    Icelandic places and Reykjavik

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

    Iceland and Icelandic

    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
    伢
    0.48
    nail
    0.47
    ledo
    0.45
    borough
    0.44
    കൊ
    0.44
    ahue
    0.44
    ríamos
    0.43
    歼
    0.43
    #-
    0.42
    antoin
    0.41
    POSITIVE LOGITS
     Icelandic
    1.48
    Iceland
    1.41
     Iceland
    1.38
     Reykjav
    1.32
     Reykjavik
    1.31
     आइसलैंड
    0.95
     Faroe
    0.80
     Þ
    0.77
    Þ
    0.74
     Greenland
    0.67
    Activations Density 0.033%

    No Known Activations