© 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. 64397
    Prev
    Next
    INDEX
    Explanations

    diagnostic ultrasoundthorough analysisdeliver smartphonesvariety of

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

    frominofand

    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
    autorisation
    0.55
    जम
    0.52
    विभाग
    0.51
    UMPS
    0.50
    পৃথিব
    0.50
    靔
    0.50
    ඕ
    0.50
    ொருள்
    0.49
    তল
    0.49
    オーバー
    0.49
    POSITIVE LOGITS
     prov
    0.50
     hel
    0.48
    s
    0.47
     Janice
    0.46
     gaping
    0.44
     dev
    0.44
     Kafka
    0.44
     pret
    0.43
     Jenkins
    0.43
     pretend
    0.43
    Activations Density 0.000%

    No Known Activations