© 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. 15697
    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
    erunner
    -1.23
    atories
    -1.15
    hadapi
    -1.13
    愀
    -1.13
    vably
    -1.09
    кос
    -1.09
     fhould
    -1.08
    unción
    -1.07
    fordshire
    -1.06
     münchen
    -1.06
    POSITIVE LOGITS
     –
    1.07
    (
    1.02
     of
    1.02
     with
    1.00
     priori
    1.00
    </strong>
    0.98
     (
    0.94
     plans
    0.92
     acompañ
    0.91
    </u>
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.