© 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. 111983
    Prev
    Next
    INDEX
    Explanations

    order of or requesting

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

    order followed by specifications

    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
    ]
    0.86
    দ
    0.84
    ্য
    0.80
    $
    0.79
    ิน
    0.78
    }
    0.73
     or
    0.73
    ו
    0.71
     are
    0.69
     atlet
    0.69
    POSITIVE LOGITS
    Order
    1.45
     Order
    1.39
    order
    1.38
     주문
    1.34
     Ordering
    1.26
    getOrder
    1.25
    Ordering
    1.24
     order
    1.22
     ORDER
    1.22
     ऑर्डर
    1.20
    Activations Density 0.080%

    No Known Activations