© 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. 44121
    Prev
    Next
    INDEX
    Explanations

    quantifying estimates and ranges

    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
     know
    -1.35
     on
    -1.18
     oficialmente
    -1.14
     hating
    -1.09
     will
    -1.08
    chaikovsky
    -1.08
    但是在
    -1.07
     speculating
    -1.07
    除此
    -1.05
     obfer
    -1.05
    POSITIVE LOGITS
    ኧ
    1.50
     Capacidad
    1.31
    ∛
    1.30
     если
    1.30
    Configured
    1.28
    </b>
    1.27
    zość
    1.20
     они
    1.19
     новый
    1.19
     работает
    1.18
    Activations Density 0.072%

    No Known Activations