© 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. 186088
    Prev
    Next
    INDEX
    Explanations

    insurance, launch, home decor

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

    United States", "first in", "me correctly"

    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
     welds
    0.50
    大的
    0.48
    ក្រោម
    0.47
     টাকা
    0.47
     vontade
    0.47
     straps
    0.46
     уй
    0.45
    }^{*},
    0.45
     época
    0.45
     बड़े
    0.44
    POSITIVE LOGITS
     TCE
    0.45
     Dis
    0.43
     Contracting
    0.41
     Marcel
    0.41
    㥆
    0.41
    蓯
    0.41
     DBE
    0.40
     classification
    0.39
    詠
    0.39
    섣
    0.39
    Activations Density 0.001%

    No Known Activations