© 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. 10-GEMMASCOPE-RES-131K
    7. 129672
    Prev
    Next
    INDEX
    Explanations

    moreover ,

    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_10/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
    蠵
    -2.36
    },
    -2.25
     to
    -2.03
    ',
    -2.00
    ]:
    -1.98
    .,
    -1.97
    ",
    -1.93
     voor
    -1.91
     ine
    -1.91
    }(
    -1.90
    POSITIVE LOGITS
     Moreover
    2.47
    鹮
    2.42
     rumbling
    2.28
    渼
    2.20
    秶
    2.20
     Furthermore
    2.14
    瀉
    1.98
     anún
    1.98
    8
    1.95
    殽
    1.95
    Activations Density 0.007%

    No Known Activations