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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 122617
    Prev
    Next
    INDEX
    Explanations

    list items and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite

    contrasting conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oxfordshire
    0.54
    Ἀ
    0.49
     interactive
    0.47
     nutrients
    0.45
     They
    0.44
     Moreton
    0.44
     Sutherland
    0.43
     imaging
    0.43
     Bournemouth
    0.43
     नील
    0.42
    POSITIVE LOGITS
     beban
    0.45
    िवेशन
    0.44
    笳
    0.44
    صير
    0.43
    大多數
    0.43
     през
    0.43
    醫院
    0.43
     пого
    0.42
     للق
    0.42
    BATCH
    0.42
    Activations Density 0.002%

    No Known Activations