© 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. 34-GEMMASCOPE-RES-131K
    4. 34468
    Prev
    Next
    INDEX
    Explanations

    programming code 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_34/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
     gide
    -0.91
    "});
    -0.85
    běh
    -0.80
    chowy
    -0.79
     tene
    -0.79
    零售
    -0.78
     увидел
    -0.78
     duran
    -0.75
    empre
    -0.73
    骑士
    -0.73
    POSITIVE LOGITS
    ?.
    2.50
    ()?.
    2.16
    ?
    2.13
    ]?.
    2.06
    )?.
    1.57
    FirstOrDefault
    1.48
    ?)
    1.48
    ?).
    1.37
    ?”
    1.23
     может
    1.14
    Activations Density 0.009%

    No Known Activations