© 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. 52230
    Prev
    Next
    INDEX
    Explanations

    foreign words and scripts

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

    decimal resort country sounds

    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
     altern
    0.49
     vitro
    0.48
    cv
    0.47
    u
    0.46
    ko
    0.46
    degener
    0.44
    a
    0.44
    us
    0.43
    kor
    0.43
    i
    0.43
    POSITIVE LOGITS
    Привет
    0.46
    境外
    0.45
    ljena
    0.45
     शराब
    0.44
    Government
    0.43
     คิด
    0.43
    lahir
    0.43
     அஜித்
    0.43
    โร
    0.43
    อร
    0.43
    Activations Density 0.001%

    No Known Activations