© 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. 111831
    Prev
    Next
    INDEX
    Explanations

    quality of description

    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
    <0x1D>
    0.44
    ahrer
    0.42
    yss
    0.40
     предпочита
    0.40
     harms
    0.39
    aturamento
    0.39
    inheritdoc
    0.38
    intu
    0.37
    usions
    0.37
     नुकसान
    0.37
    POSITIVE LOGITS
     refined
    0.43
     waste
    0.39
     COL
    0.39
    ]]:
    0.38
    Waste
    0.37
     wyróż
    0.36
     tos
    0.36
    廢
    0.36
    refined
    0.36
    ំពោះ
    0.36
    Activations Density 0.001%

    No Known Activations