© 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. 73282
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     frattempo
    -1.23
     ferie
    -1.17
     fhall
    -1.16
     ftill
    -1.13
     italiens
    -1.13
     Schweiz
    -1.09
     Italie
    -1.08
     etui
    -1.07
     radeon
    -1.07
     faid
    -1.05
    POSITIVE LOGITS
     each
    1.04
     how
    1.03
     know
    1.02
     also
    1.00
     has
    0.97
    zać
    0.93
     außerdem
    0.93
     by
    0.92
    点评
    0.91
    ]
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.