© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8388
    Prev
    Next
    INDEX
    Explanations

    names and specific locations

    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
    钲
    -2.66
    ਲ਼
    -2.58
    桄
    -2.45
    仉
    -2.38
    しちゃ
    -2.38
    紲
    -2.34
     whom
    -2.33
    鏷
    -2.33
    拶
    -2.31
     vorliegenden
    -2.30
    POSITIVE LOGITS
    ’
    2.38
    ]
    2.38
    灕
    2.34
    …»
    2.20
    的那
    2.02
     
    1.96
     (…)
    1.96
    ти
    1.93
    …).
    1.92
    ”…
    1.91
    Activations Density 0.002%

    No Known Activations