© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5829
    Prev
    Next
    INDEX
    Explanations

    mu followed by specific words

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

    mu or muc beginnings

    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_53_width_65k_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
    maur
    0.43
    mission
    0.39
    oises
    0.39
    terus
    0.38
    앓
    0.37
    mongodb
    0.37
    pase
    0.37
    omotor
    0.37
    ocate
    0.37
    opa
    0.36
    POSITIVE LOGITS
     mu
    0.66
    Mu
    0.61
     MU
    0.59
     Mu
    0.58
    herjee
    0.52
    ніципа
    0.52
    穆
    0.50
    릎
    0.50
    mu
    0.50
     му
    0.49
    Activations Density 0.046%

    No Known Activations