© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 235675
    Prev
    Next
    INDEX
    Explanations

    tuned in

    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
    Negative Logits
    recyclerView
    0.46
     llena
    0.46
    晶
    0.46
    encies
    0.45
    ]->
    0.42
    ]//
    0.42
    introducing
    0.42
    berries
    0.42
    ;
    0.42
    }\}$
    0.41
    POSITIVE LOGITS
     liquid
    0.48
     spender
    0.48
     کف
    0.47
     clamp
    0.46
     montée
    0.46
     machine
    0.46
     spent
    0.46
     convective
    0.46
     spectacle
    0.46
     front
    0.46
    Activations Density 0.001%

    No Known Activations