© 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. 190790
    Prev
    Next
    INDEX
    Explanations

    procurement, stillness, interviews, quantity, shop, selection, admit

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

    framed as

    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
    
    0.41
    飞机
    0.40
     tulle
    0.40
     رغم
    0.39
     lego
    0.38
    Inj
    0.38
     liar
    0.38
    ป
    0.37
    িংস
    0.37
    อา
    0.36
    POSITIVE LOGITS
     obligación
    0.49
    プーン
    0.47
     obligated
    0.47
     विवेक
    0.46
     Público
    0.45
     продав
    0.44
     Hương
    0.44
    ဝန်
    0.44
     nécessairement
    0.44
     Ч
    0.43
    Activations Density 0.001%

    No Known Activations