© 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. 97725
    Prev
    Next
    INDEX
    Explanations

    setup and backups

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

    no difference

    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
     messaging
    0.45
    প্র
    0.44
     tweaks
    0.43
    𝐞
    0.43
    udd
    0.43
    📞
    0.43
    פי
    0.42
    𝘦
    0.41
    ives
    0.41
    endedores
    0.41
    POSITIVE LOGITS
     зміню
    0.53
    ITERATURE
    0.49
     mnoho
    0.47
     aanwezig
    0.45
     sujeito
    0.44
     شرطونه
    0.44
     contributory
    0.43
     alltid
    0.43
     வைத்திய
    0.43
    颢
    0.43
    Activations Density 0.001%

    No Known Activations