© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2077
    Prev
    Next
    INDEX
    Explanations

    efficiency, can, come

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     strategy
    1.04
     method
    0.96
    dated
    0.96
     strategies
    0.94
     (£
    0.94
     organisation
    0.94
    idated
    0.94
     historians
    0.94
    맬
    0.93
     strategist
    0.92
    POSITIVE LOGITS
    7
    1.22
    rinsic
    1.22
    8
    1.14
    6
    1.10
    Entities
    1.00
    ຖານ
    0.99
     επο
    0.99
     объекты
    0.98
    Чу
    0.97
     obecnie
    0.97
    Activations Density 0.577%

    No Known Activations