© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1402
    Prev
    Next
    INDEX
    Explanations

    you might also like

    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_40_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
    ।,
    0.48
     drunkenness
    0.42
    壊
    0.38
     аўта
    0.38
    ]^{-
    0.37
     preocupaciones
    0.36
    ]=='
    0.36
     rumores
    0.36
     stench
    0.35
    屢
    0.35
    POSITIVE LOGITS
     interesting
    0.67
     interested
    0.66
     interes
    0.64
     consider
    0.59
     интересно
    0.58
     interesa
    0.57
     интерес
    0.57
     interessante
    0.56
     interessant
    0.56
     interessiert
    0.56
    Activations Density 0.000%

    No Known Activations