© 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. 117406
    Prev
    Next
    INDEX
    Explanations

    manufacturing machinery and components

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

    precisely controlled by machines

    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
     ಉತ್ಪನ್ನ
    0.46
    bitflag
    0.46
    MeshData
    0.45
    㴼
    0.44
    阈
    0.43
     एरो
    0.43
     GoObject
    0.42
     stry
    0.42
    鹿
    0.42
    MinIntensity
    0.42
    POSITIVE LOGITS
     rollers
    0.59
     roller
    0.49
     Roller
    0.49
     машины
    0.47
     Machines
    0.45
     machines
    0.45
     rollback
    0.45
     Rape
    0.45
     raping
    0.44
     descansar
    0.44
    Activations Density 0.085%

    No Known Activations