© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11510
    Prev
    Next
    INDEX
    Explanations

    place names in geographical contexts

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

    place name components

    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_40_width_16k_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
    唓
    0.61
    ፧
    0.59
     אטאטורק
    0.59
     Unternehmer
    0.58
    ᓘ
    0.56
     Reykjavik
    0.55
    Ciudad
    0.54
    Lyon
    0.54
    蕞
    0.54
     ۋ
    0.54
    POSITIVE LOGITS
    amb
    0.47
    long
    0.44
    ul
    0.43
    pat
    0.42
    anda
    0.41
    ase
    0.41
    jul
    0.41
    op
    0.41
    opens
    0.41
    ip
    0.40
    Activations Density 0.120%

    No Known Activations