© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59449
    Prev
    Next
    INDEX
    Explanations

    what the heck/hell/fuck

    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
    鹪
    -2.22
    𓆏
    -2.08
     trám
    -1.89
    骘
    -1.88
    вгений
    -1.86
    𓁹
    -1.85
     搞笑
    -1.85
     elétrica
    -1.84
     desaparición
    -1.82
     ferrovia
    -1.81
    POSITIVE LOGITS
     it
    1.77
     these
    1.62
     he
    1.62
     those
    1.59
    ↵
    1.59
    <em>
    1.55
     /
    1.55
    のは
    1.52
    a
    1.50
     ecstasy
    1.49
    Activations Density 0.002%

    No Known Activations