© 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. 218940
    Prev
    Next
    INDEX
    Explanations

    describes actions and states

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

    listing disadvantages

    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
     социального
    0.47
    사람
    0.46
    극한
    0.46
    escaping
    0.45
    ванні
    0.45
    윤
    0.45
     выс
    0.44
    셉
    0.43
     Еўропы
    0.43
     находя
    0.43
    POSITIVE LOGITS
    za
    0.55
     heifers
    0.52
     regulator
    0.52
     tanks
    0.50
     lettuce
    0.48
    pyrimidine
    0.48
     me
    0.47
     orchard
    0.47
     needed
    0.47
     joy
    0.46
    Activations Density 0.001%

    No Known Activations