© 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. 109217
    Prev
    Next
    INDEX
    Explanations

    knowledge graph relations

    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
    ٘
    0.42
     levant
    0.41
     planis
    0.39
     understandings
    0.38
    ᕆ
    0.38
    荩
    0.38
    stove
    0.38
    ᅱ
    0.37
     Conley
    0.37
     caldera
    0.37
    POSITIVE LOGITS
    Kg
    0.47
     кг
    0.46
     Kg
    0.46
    Negative
    0.44
     kg
    0.44
     Types
    0.43
     KG
    0.43
    kg
    0.42
     Negative
    0.42
    ANK
    0.39
    Activations Density 0.017%

    No Known Activations