© 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. 165395
    Prev
    Next
    INDEX
    Explanations

    London or DC/OS

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

    government and law

    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
    minsize
    0.51
     inú
    0.50
     numerosas
    0.47
     }{}_{\
    0.47
     ऑर्गेनाइजेशन
    0.47
    帳に追加
    0.47
     многочис
    0.47
     同时
    0.46
     numerosos
    0.46
     ಯು
    0.46
    POSITIVE LOGITS
    となって
    0.61
    ティ
    0.49
     can
    0.47
    Joh
    0.46
    それでは
    0.46
    Imp
    0.45
    LONDON
    0.44
    London
    0.44
    7
    0.44
    oi
    0.43
    Activations Density 0.001%

    No Known Activations