© 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. 85733
    Prev
    Next
    INDEX
    Explanations

    translation

    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
    ers
    -1.99
     så
    -1.98
    ("
    -1.91
    /
    -1.91
    ஂ
    -1.91
     diesem
    -1.89
    ᨈ
    -1.88
     welchem
    -1.84
     той
    -1.84
                 
    -1.84
    POSITIVE LOGITS
     respected
    2.22
     OGSÅ
    2.22
     Geräten
    2.19
    甞
    2.14
     parís
    2.13
     postIndex
    2.09
    珢
    2.09
    龵
    2.08
    geſ
    2.03
    戆
    2.02
    Activations Density 0.030%

    No Known Activations