© 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. 195582
    Prev
    Next
    INDEX
    Explanations

    organizations, mind, weeks, period

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

    planning for specific futures

    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
    brook
    0.44
    al
    0.43
    r
    0.43
     nies
    0.42
     Sweep
    0.41
    rzed
    0.41
     대상으로
    0.41
     Cuomo
    0.41
     Roche
    0.40
     ailes
    0.40
    POSITIVE LOGITS
    パーカー
    0.51
     பிர
    0.51
    ститу
    0.50
    購買
    0.50
    電
    0.47
    स्तिष्क
    0.47
    開始
    0.46
    電子
    0.46
    電圧
    0.45
    电子
    0.45
    Activations Density 0.000%

    No Known Activations