© 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. 212550
    Prev
    Next
    INDEX
    Explanations

    ZigBee, millions users

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

    sequences after words like "T cell", "Beyond", "Workflow", "Sansa"

    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
    互联网档案馆
    0.44
    continuity
    0.44
    asyon
    0.43
     pathologic
    0.43
     continuity
    0.43
    ysed
    0.41
     फ़रवरी
    0.41
    児
    0.39
    明显的
    0.39
     चेयरमैन
    0.39
    POSITIVE LOGITS
    '
    0.54
     }),
    0.50
    edd
    0.50
     })
    0.50
    exch
    0.49
    न
    0.48
     pena
    0.46
     },
    0.46
     dupatta
    0.46
     eddy
    0.46
    Activations Density 0.000%

    No Known Activations