© 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. 9895
    Prev
    Next
    INDEX
    Explanations

    space exploration and astronauts

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

    space, spacecraft, and exploration

    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
     phường
    0.68
    慵
    0.65
     власть
    0.59
     натура
    0.58
     арифмети
    0.58
     Punjabi
    0.57
     നല്ല
    0.56
    💆
    0.56
    汴
    0.56
    忿
    0.55
    POSITIVE LOGITS
     NASA
    1.81
    NASA
    1.70
     spacecraft
    1.65
     astronaut
    1.55
     astronauts
    1.45
     aerospace
    1.32
     Astronaut
    1.25
     nasa
    1.23
     SpaceX
    1.23
    astronaut
    1.23
    Activations Density 0.154%

    No Known Activations