© 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. 14338
    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
     Behörden
    -1.10
     maravilh
    -1.09
    はっきり
    -1.05
     Then
    -1.02
     governador
    -1.01
    Տ
    -0.91
     Muito
    -0.91
    gilet
    -0.91
    melhor
    -0.88
     것입니다
    -0.87
    POSITIVE LOGITS
    </h2>
    1.02
    کارت
    0.97
    hlte
    0.96
     VICT
    0.96
     FIRM
    0.94
     Wasp
    0.93
    GENERIC
    0.92
     iran
    0.92
     Indias
    0.90
    Adv
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.