© 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. 184752
    Prev
    Next
    INDEX
    Explanations

    or if

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

    including risk or someone is

    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
     derives
    0.53
     occurs
    0.51
     delivers
    0.50
     Service
    0.49
     override
    0.49
     surfaces
    0.49
     service
    0.48
    ,
    0.48
     shows
    0.47
     output
    0.47
    POSITIVE LOGITS
    зил
    0.53
     유럽
    0.47
    Ꭻ
    0.46
    𒄖
    0.46
    Ethn
    0.46
    当該
    0.45
     அறிகுற
    0.45
     कुलकर्णी
    0.45
    toggleClass
    0.44
     Avrupa
    0.44
    Activations Density 0.001%

    No Known Activations