© 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. 26126
    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
     if
    -1.23
     desfile
    -1.20
     \%$,
    -1.16
    ]$,
    -1.13
    delingen
    -1.11
    ୈ
    -1.10
    caron
    -1.09
    ِن
    -1.09
    Without
    -1.09
    zkopf
    -1.07
    POSITIVE LOGITS
     same
    1.42
    だろ
    1.35
    zelfde
    1.27
     dasselbe
    1.18
     viendo
    1.16
     dejando
    1.13
    了许多
    1.13
    เดียว
    1.07
     neighboring
    1.07
     prachtige
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.