© 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. 194786
    Prev
    Next
    INDEX
    Explanations

    upgrade and upkeep

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

    performance metrics and upgrades

    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
    шке
    0.55
    㽡
    0.50
    jskiej
    0.50
    propelled
    0.50
     klicken
    0.48
    applicazione
    0.48
     буде
    0.47
    襞
    0.47
     подписа
    0.47
    cuando
    0.46
    POSITIVE LOGITS
     upgrade
    0.47
     upgrades
    0.47
     upgraded
    0.44
     throwback
    0.44
     stabilize
    0.43
     Addition
    0.43
     upkeep
    0.42
     Stadium
    0.41
     Emory
    0.41
     midpoint
    0.41
    Activations Density 0.000%

    No Known Activations