© 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. 49311
    Prev
    Next
    INDEX
    Explanations

    mechanisms and robots

    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
    zeczytaj
    -0.88
    σει
    -0.85
     ↓,
    -0.79
    oshi
    -0.77
    Zombie
    -0.74
    vités
    -0.74
    undu
    -0.74
    ItemID
    -0.73
    rope
    -0.73
    cần
    -0.73
    POSITIVE LOGITS
     mech
    1.94
     robot
    1.53
     robots
    1.48
     mecha
    1.45
    mech
    1.44
     Mech
    1.30
     pilo
    1.27
     mechan
    1.22
    Mech
    1.17
     machines
    1.16
    Activations Density 0.035%

    No Known Activations