© 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. 151526
    Prev
    Next
    INDEX
    Explanations

    just push

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

    discussion, information exchange, policy, personal stories

    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
    淑
    0.54
     Aguilera
    0.48
    蹑
    0.48
    APK
    0.48
     verdadeiro
    0.47
     terceiro
    0.46
    RDD
    0.46
    섣
    0.46
     আইনজীবী
    0.46
     sétimo
    0.46
    POSITIVE LOGITS
     workshop
    0.46
     forum
    0.46
     cheaper
    0.46
     forums
    0.44
     cheap
    0.43
    вання
    0.43
    cribing
    0.42
     subspace
    0.42
    ان
    0.41
     countryside
    0.41
    Activations Density 0.000%

    No Known Activations