© 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. 136490
    Prev
    Next
    INDEX
    Explanations

    locations and events

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

    non-English scripts

    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
    ?
    0.50
     perovsk
    0.48
     reduces
    0.48
     seawater
    0.47
     reduzir
    0.47
     pays
    0.46
     aquifers
    0.46
     microwaves
    0.45
     develops
    0.45
     Retail
    0.45
    POSITIVE LOGITS
    เร
    0.47
     思っ
    0.44
     шля
    0.41
     :\
    0.41
    มนเชสเตอร์
    0.41
    detailID
    0.41
     Allentown
    0.41
    ಗಳನ್ನು
    0.41
     실패
    0.40
     correctement
    0.40
    Activations Density 0.001%

    No Known Activations