© 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. 150484
    Prev
    Next
    INDEX
    Explanations

    cutlery sets, visited by, receiving a, would ring, even though, current trends

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

    potential modern genuine opinion

    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
     کتاب
    0.44
     cranking
    0.43
     kec
    0.43
    лькі
    0.42
     crater
    0.42
    小さい
    0.42
    ❶
    0.42
     soal
    0.41
     milling
    0.41
     slime
    0.41
    POSITIVE LOGITS
    }={\
    0.50
    โมง
    0.50
    句話
    0.48
    }+{\
    0.45
     કરશે
    0.45
    喰
    0.44
    }-
    0.44
     Eshelby
    0.43
     นิ
    0.43
     الحالة
    0.43
    Activations Density 0.000%

    No Known Activations