© 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. 10-GEMMASCOPE-RES-131K
    7. 119976
    Prev
    Next
    INDEX
    Explanations

    you can or should

    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
     برانيه
    -1.60
     our
    -1.54
     ersche
    -1.48
    zegovina
    -1.47
    鲆
    -1.44
     erschienen
    -1.40
     nabíz
    -1.36
    ,”
    -1.35
    歃
    -1.34
    )—
    -1.33
    POSITIVE LOGITS
    už
    1.76
    </h2>
    1.49
     overpowering
    1.45
     новая
    1.41
    言えば
    1.41
    u
    1.31
     other
    1.30
     intensify
    1.26
     encounters
    1.25
    риев
    1.25
    Activations Density 0.031%

    No Known Activations