© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11080
    Prev
    Next
    INDEX
    Explanations

    assignment and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deswegen
    0.35
    女
    0.32
    食
    0.32
    yled
    0.31
    loxy
    0.31
     pasture
    0.31
    URY
    0.31
     sostegno
    0.31
     까
    0.30
     놓고
    0.30
    POSITIVE LOGITS
     the
    0.38
     Fannie
    0.32
     Government
    0.32
     poco
    0.32
     Principal
    0.31
     उनकी
    0.31
     toda
    0.31
    ிருக்கும்
    0.30
     com
    0.30
     their
    0.30
    Activations Density 0.128%

    No Known Activations