© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2109
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence

    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_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
    ="#
    0.42
    arrows
    0.41
     introd
    0.41
    icksburg
    0.38
    ungs
    0.38
     échanc
    0.38
    nales
    0.38
     rite
    0.37
    ੍
    0.36
    ahon
    0.36
    POSITIVE LOGITS
     AI
    1.59
    人工智能
    1.59
    AI
    1.42
     robot
    1.32
     Artificial
    1.30
     algorithms
    1.28
     robots
    1.27
    Artificial
    1.26
     алгорит
    1.23
     robotic
    1.20
    Activations Density 1.158%

    No Known Activations