© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 140717
    Prev
    Next
    INDEX
    Explanations

    prepuce, RedHot, DCT, statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.59
     fatally
    0.59
     rocker
    0.57
    f
    0.56
     へ
    0.55
     quirky
    0.54
     weapons
    0.53
    fühl
    0.52
    ir
    0.50
     elite
    0.50
    POSITIVE LOGITS
    то
    0.63
    ιτε
    0.56
    τητας
    0.55
    й
    0.51
     docentes
    0.50
    𝚌
    0.49
    стойчи
    0.48
     количе
    0.48
     IUE
    0.48
    थरूम
    0.48
    Activations Density 0.000%

    No Known Activations