© 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. 44483
    Prev
    Next
    INDEX
    Explanations

    describing things as mysterious

    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
    澌
    -1.62
    糁
    -1.57
    齜
    -1.53
    𝒰
    -1.52
    轂
    -1.49
    </h6>
    -1.48
    髣
    -1.47
    recently
    -1.47
    </em>
    -1.44
    ཥ
    -1.44
    POSITIVE LOGITS
    其妙
    1.97
     mutta
    1.62
     about
    1.55
     why
    1.54
    ligibility
    1.52
     strangely
    1.51
     and
    1.47
    abancı
    1.46
    何故
    1.45
    sterious
    1.43
    Activations Density 0.053%

    No Known Activations