© 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. 22-GEMMASCOPE-RES-131K
    7. 27024
    Prev
    Next
    INDEX
    Explanations

    the end punctuation

    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
    ệu
    -1.13
    gląda
    -0.98
    hamdulillah
    -0.97
    »),
    -0.95
    сумка
    -0.95
    ])]
    -0.91
    ์
    -0.90
    }',
    -0.88
     it
    -0.88
    ن
    -0.88
    POSITIVE LOGITS
     these
    1.44
     also
    1.34
    hichever
    1.24
     all
    1.24
     außerdem
    1.23
     остальных
    1.20
    いずれ
    1.16
    これらの
    1.16
     plus
    1.15
     lisäksi
    1.09
    Activations Density 0.020%

    No Known Activations