© 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. 22-GEMMASCOPE-RES-131K
    7. 129170
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     your
    -1.26
     will
    -1.25
    -
    -1.23
    Цены
    -1.15
    etna
    -1.15
    odles
    -1.11
     anpass
    -1.09
     situe
    -1.09
    izamos
    -1.09
    vaila
    -1.07
    POSITIVE LOGITS
     أخرى
    1.15
    autres
    1.06
     других
    1.06
     другим
    1.06
    其他
    1.06
    ronym
    1.05
    健身
    1.05
    بالإنجليزية
    1.03
    Biografie
    1.03
     other
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.