© 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. 71256
    Prev
    Next
    INDEX
    Explanations

    reputable and trustworthy

    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
     altijd
    -1.67
    閙
    -1.66
     about
    -1.66
    utenant
    -1.49
     reú
    -1.47
    gunakan
    -1.45
    ilem
    -1.44
    🪤
    -1.41
    ⎆
    -1.41
     it
    -1.39
    POSITIVE LOGITS
    ↵
    1.55
     ‘
    1.45
    };
    1.41
     and
    1.40
    f
    1.38
     trustworthy
    1.37
    ‘
    1.36
     –
    1.35
    </u>
    1.30
    “,
    1.30
    Activations Density 0.016%

    No Known Activations