© 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. 80363
    Prev
    Next
    INDEX
    Explanations

    lynching, penalty, call, contact, new

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

    lists of items

    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
    ad
    0.49
    >..\
    0.46
    im
    0.46
    ari
    0.45
     ಆದ
    0.44
    ierung
    0.44
    prüsü
    0.44
    og
    0.43
    uman
    0.43
    大了
    0.42
    POSITIVE LOGITS
     faceted
    0.49
    ້ອ
    0.48
    های
    0.48
     dechlorination
    0.45
    
    0.45
     you
    0.45
     thé
    0.45
     locking
    0.45
     mq
    0.45
     fracking
    0.44
    Activations Density 0.000%

    No Known Activations