© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54252
    Prev
    Next
    INDEX
    Explanations

    star ratings and numbers

    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
    istán
    -1.20
    ########.
    -1.13
    ">"
    -1.03
    ร้าน
    -1.02
    فیلم
    -0.99
    entown
    -0.98
    estrian
    -0.97
    foods
    -0.97
    getDay
    -0.97
    }}}}
    -0.96
    POSITIVE LOGITS
    為に
    1.08
     Какой
    0.99
     Зачем
    0.98
    1
    0.98
     Deiner
    0.97
    忘れて
    0.97
     όμως
    0.96
    I
    0.96
     rác
    0.96
     czarny
    0.95
    Activations Density 0.021%

    No Known Activations