© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 43983
    Prev
    Next
    INDEX
    Explanations

    Croatia and Croatian related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conductance
    0.62
     that
    0.61
    ID
    0.61
     света
    0.59
     ultime
    0.59
     al
    0.58
     alight
    0.58
    ]];
    0.57
     بود
    0.56
     cadence
    0.56
    POSITIVE LOGITS
     Croatian
    0.85
     Croatia
    0.80
     Hrvatskoj
    0.77
     Hrvats
    0.72
    Croatian
    0.71
     Dubrovnik
    0.68
     hrvats
    0.67
    𝕀
    0.67
    very
    0.63
    昻
    0.63
    Activations Density 0.003%

    No Known Activations