© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129604
    Prev
    Next
    INDEX
    Explanations

    packed, crowded, cramped, squeezed

    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
     –
    -1.62
    ibição
    -1.43
    都是
    -1.34
     divi
    -1.25
    About
    -1.20
    要
    -1.20
    豨
    -1.20
    毋
    -1.17
    -1.16
    ॠ
    -1.15
    POSITIVE LOGITS
    嫱
    1.57
    llavero
    1.52
    čky
    1.41
    柺
    1.34
     aceite
    1.30
    龘
    1.30
    Условия
    1.27
     烤
    1.24
    配备
    1.22
     between
    1.20
    Activations Density 0.042%
    No Known Activations