© 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. 11393
    Prev
    Next
    INDEX
    Explanations

    city names followed by punctuation

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

    cities in India and Pakistan

    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
    纽约
    0.42
     jednom
    0.41
     छेद
    0.41
     стол
    0.40
     ένας
    0.39
    ₂)
    0.39
     କ
    0.39
    hitth
    0.38
     വിദ
    0.38
     США
    0.38
    POSITIVE LOGITS
     pwd
    0.41
     goodies
    0.38
     preferential
    0.36
     xmas
    0.36
    😙
    0.34
     wifi
    0.33
     drastic
    0.33
    优惠
    0.33
     political
    0.32
     mism
    0.32
    Activations Density 0.000%

    No Known Activations