© 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. 44548
    Prev
    Next
    INDEX
    Explanations

    mono to

    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
     letzte
    -1.84
    ch
    -1.51
    in
    -1.49
    TEM
    -1.48
     letzten
    -1.45
    RE
    -1.44
    สุด
    -1.39
     betreffende
    -1.39
    iding
    -1.38
     dritte
    -1.38
    POSITIVE LOGITS
     сказал
    1.79
    錚
    1.62
    zló
    1.59
     場所
    1.59
    onatos
    1.55
    hoenix
    1.53
    stornos
    1.50
    cipline
    1.49
    atric
    1.49
    </h4>
    1.48
    Activations Density 0.005%

    No Known Activations