© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47740
    Prev
    Next
    INDEX
    Explanations

    valve and followers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ringen
    -0.86
    范文
    -0.74
     rings
    -0.74
     δή
    -0.69
     Noviembre
    -0.69
     holiday
    -0.69
     фрук
    -0.68
    
    -0.68
    を重ね
    -0.68
     ring
    -0.66
    POSITIVE LOGITS
     rocker
    1.49
     rockers
    1.45
     lifter
    1.19
     Rocker
    1.16
     tapp
    1.14
     follower
    1.13
     followers
    1.13
    followers
    1.10
    follower
    1.09
    Follower
    1.05
    Activations Density 0.015%

    No Known Activations