© 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. 122087
    Prev
    Next
    INDEX
    Explanations

    locations and charges

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

    European destinations and travel

    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
     কিছুক্ষণ
    0.51
    麋
    0.49
    密的
    0.46
    鮭
    0.44
    きたい
    0.43
    協會
    0.43
    鹿
    0.43
     إص
    0.42
    鱒
    0.41
    芻
    0.41
    POSITIVE LOGITS
     Cyprus
    0.51
    Europa
    0.49
     Lanzarote
    0.47
     Europa
    0.45
     failings
    0.44
     Crete
    0.44
     criminality
    0.44
     €
    0.44
     europa
    0.44
     Griechen
    0.44
    Activations Density 0.061%

    No Known Activations