© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1653
    Prev
    Next
    INDEX
    Explanations

    gravity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flaring
    -0.77
     Gln
    -0.76
    tableFuture
    -0.72
    芙
    -0.71
    faceted
    -0.70
    žių
    -0.70
     GONZ
    -0.68
     darb
    -0.68
    lidades
    -0.67
     kurie
    -0.66
    POSITIVE LOGITS
     gravity
    6.78
    gravity
    5.69
     Gravity
    5.41
    Gravity
    5.19
     gravitational
    4.03
    GRAV
    3.81
     gravedad
    3.80
     GRAV
    3.80
     gravitation
    3.30
    setGravity
    2.80
    Activations Density 0.055%

    No Known Activations