© 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. 28795
    Prev
    Next
    INDEX
    Explanations

    catamaran lover

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

    cleansing sprint, attempting to direct

    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
    B
    0.62
    L
    0.50
    am
    0.50
    olio
    0.49
    argo
    0.48
    </h3>
    0.48
    arp
    0.48
    ToString
    0.47
    T
    0.47
    AI
    0.47
    POSITIVE LOGITS
     peneliti
    0.57
     launchers
    0.55
     lancement
    0.52
     lançamento
    0.50
     créer
    0.49
     لیست
    0.49
     cliquez
    0.49
     местные
    0.48
     aplicado
    0.48
    произ
    0.48
    Activations Density 0.000%

    No Known Activations