© 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. 25436
    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
     both
    -1.37
     every
    -1.27
     this
    -1.23
     each
    -1.12
     helps
    -1.08
    mappedBy
    -1.05
     just
    -1.04
     only
    -1.03
     sevilla
    -1.02
     during
    -0.99
    POSITIVE LOGITS
    Alternatively
    1.40
     alternatively
    1.37
     Alternatively
    1.35
     Однако
    1.10
     Также
    1.09
    however
    1.07
    ighth
    1.06
     Эти
    1.05
    ropia
    1.01
     difíciles
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.