© 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. 6501
    Prev
    Next
    INDEX
    Explanations

    the [word]

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

    "Minas" or "colonia Del Valle

    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
    gano
    0.46
    秶
    0.44
    osite
    0.41
     Vote
    0.39
    ٰی
    0.39
    ですので
    0.38
     Aut
    0.38
     McCabe
    0.38
     give
    0.37
    /.
    0.37
    POSITIVE LOGITS
     polypes
    0.49
     philippines
    0.46
     bloodstream
    0.45
     requester
    0.45
     interstices
    0.43
     abdomen
    0.42
     కార్డు
    0.42
     same
    0.41
     pancreas
    0.41
     mêmes
    0.40
    Activations Density 0.150%

    No Known Activations