© 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. 19772
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    geocode path

    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
    Q
    0.61
    U
    0.56
    <code>
    0.55
    S
    0.54
    Use
    0.53
    I
    0.53
    K
    0.53
    E
    0.53
    D
    0.53
    Z
    0.52
    POSITIVE LOGITS
     działalności
    0.51
     außergewöhn
    0.47
     နှစ်
    0.46
     druż
    0.46
     nejen
    0.46
     témoign
    0.46
     rappresenta
    0.45
     bestellen
    0.44
     pakaian
    0.44
     vår
    0.44
    Activations Density 0.002%

    No Known Activations