© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8918
    Prev
    Next
    INDEX
    Explanations

    capability and capacity

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

    capability and tools

    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_40_width_16k_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
     aspects
    0.42
     對
    0.40
     Aspects
    0.39
    osha
    0.39
    winfx
    0.39
    使
    0.38
    kj
    0.38
    活用
    0.37
     observable
    0.37
     aspectos
    0.37
    POSITIVE LOGITS
     capability
    0.93
    能力
    0.88
    capability
    0.84
     ability
    0.78
     Capability
    0.78
     capacity
    0.75
     능력
    0.75
     capacità
    0.75
     capacidad
    0.74
     capacité
    0.73
    Activations Density 0.228%

    No Known Activations