© 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. 222440
    Prev
    Next
    INDEX
    Explanations

    courier delivered

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

    technical knowledge and brain function

    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
    макра
    0.59
    ﺬ
    0.53
    コイン
    0.51
    ション
    0.50
    ემა
    0.50
     மன்ற
    0.50
    ﻀ
    0.49
     shrugged
    0.47
    ⑫
    0.47
     څنګه
    0.47
    POSITIVE LOGITS
    jk
    0.58
    io
    0.54
    Intent
    0.52
    ꞌ
    0.52
    "",
    0.50
    ott
    0.49
    Q
    0.48
    api
    0.48
    HU
    0.47
     Ahmedabad
    0.47
    Activations Density 0.001%

    No Known Activations