© 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. 58543
    Prev
    Next
    INDEX
    Explanations

    nuclear reactor

    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
    ähteet
    -0.85
     GILBERT
    -0.84
     concurso
    -0.83
     IOError
    -0.75
    tesse
    -0.75
     dương
    -0.74
    𝙟
    -0.74
     Morley
    -0.73
     pecado
    -0.72
    Oficina
    -0.72
    POSITIVE LOGITS
     reactor
    1.77
     reactors
    1.55
    reactor
    1.43
     Reactor
    1.38
     реак
    1.23
    Reactor
    1.22
     Rea
    1.08
    react
    1.06
    反应
    1.02
    Rea
    0.98
    Activations Density 0.020%

    No Known Activations