© 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. 32355
    Prev
    Next
    INDEX
    Explanations

    ambulance

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

    moving systemically

    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
    ﺟ
    0.53
    ح
    0.50
     mẽ
    0.50
    Ꭽ
    0.49
    وة
    0.49
    ⚒
    0.49
    rž
    0.48
    сор
    0.48
    коно
    0.47
     полуо
    0.47
    POSITIVE LOGITS
    钻石
    0.43
    kenalkan
    0.42
    ılabilir
    0.41
     Discourse
    0.41
     관
    0.39
    ambulance
    0.39
     Person
    0.39
    至今
    0.38
     ambulances
    0.38
     Ambulance
    0.37
    Activations Density 0.001%

    No Known Activations