© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58409
    Prev
    Next
    INDEX
    Explanations

    low Earth orbit

    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
    EnableWeb
    -0.86
    ricts
    -0.78
    Senha
    -0.75
    getReal
    -0.73
    ∭
    -0.71
    expire
    -0.70
     Agamemnon
    -0.69
     Resultat
    -0.69
    ']>
    -0.69
    dillo
    -0.68
    POSITIVE LOGITS
     orbit
    2.33
     orbits
    1.95
    Orbit
    1.32
     Low
    1.23
     Orbit
    1.23
    Low
    1.21
    orbit
    1.19
     LEO
    1.17
     low
    1.14
     elliptical
    1.12
    Activations Density 0.028%

    No Known Activations