© 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. 53-GEMMASCOPE-2-RES-262K
    7. 47281
    Prev
    Next
    INDEX
    Explanations

    Charles University and Bridge

    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_53_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
    uesto
    0.43
    ェ
    0.42
     தா
    0.39
     obligatoire
    0.38
    用紙
    0.38
     ഷ
    0.38
     inférieur
    0.37
    ы
    0.36
     potrebné
    0.36
     Schroeder
    0.36
    POSITIVE LOGITS
     risk
    0.46
    Risk
    0.45
    Embedded
    0.44
    风险
    0.43
     retrieved
    0.42
     Embedded
    0.42
     Risk
    0.42
     adventurers
    0.42
    風險
    0.41
     கண்
    0.41
    Activations Density 0.002%

    No Known Activations