© 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. 68268
    Prev
    Next
    INDEX
    Explanations

    numbered steps and stages

    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
     of
    -1.82
     with
    -1.69
    leistungs
    -1.66
    ående
    -1.60
    rativa
    -1.55
    pustakaan
    -1.50
    klju
    -1.49
    niająca
    -1.48
     primeiros
    -1.45
    сок
    -1.45
    POSITIVE LOGITS
    ,
    1.76
     each
    1.73
    かなり
    1.59
    Här
    1.59
    ar
    1.58
    珦
    1.52
     your
    1.50
    まっている
    1.49
    </b>
    1.45
     needing
    1.45
    Activations Density 0.022%

    No Known Activations