© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 120566
    Prev
    Next
    INDEX
    Explanations

    place or describing concepts

    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
    ihn
    0.43
    %).
    0.42
    亿美元
    0.42
     கவர்
    0.41
    IZA
    0.41
     ಮಾಡಲು
    0.40
     \%)$.
    0.40
    MANIFEST
    0.39
    %]
    0.38
     obdob
    0.38
    POSITIVE LOGITS
     Canada
    0.40
    ch
    0.38
     Can
    0.38
     before
    0.37
     polite
    0.37
     spaces
    0.37
     jun
    0.37
     Matthew
    0.37
     siè
    0.36
     spa
    0.36
    Activations Density 0.002%

    No Known Activations