© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67529
    Prev
    Next
    INDEX
    Explanations

    statistical and experimental design

    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_22/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
     secure
    -1.08
    。
    -1.07
    ↵↵↵
    -1.07
    ],
    -1.06
    روا
    -1.05
    ться
    -1.03
    },
    -1.02
    hang
    -1.02
    \/
    -1.01
    rounder
    -1.01
    POSITIVE LOGITS
    atschapp
    1.12
     място
    1.09
    诏
    1.06
     northeastern
    1.05
     legislature
    1.05
     държа
    1.05
     всичко
    1.03
    vosti
    1.03
     disseminating
    1.03
     взе
    1.02
    Activations Density 0.018%

    No Known Activations