© 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. 94939
    Prev
    Next
    INDEX
    Explanations

    hotels near Naples

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

    list items and descriptions

    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
     Νο
    0.46
    akiem
    0.43
    łki
    0.42
     الأه
    0.42
    ꞎ
    0.42
    र्ता
    0.41
     lắng
    0.41
     Akademi
    0.41
    ળી
    0.41
     займа
    0.41
    POSITIVE LOGITS
    data
    0.46
     pollute
    0.45
    wood
    0.45
    ारक
    0.45
     been
    0.44
    inode
    0.44
     because
    0.43
     strangely
    0.43
    雀
    0.43
     ina
    0.43
    Activations Density 0.000%

    No Known Activations