© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13330
    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
     pás
    -1.30
     pán
    -1.19
     évé
    -1.17
     mikrofon
    -1.16
     escudo
    -1.16
     autobus
    -1.16
     kupa
    -1.16
    yym
    -1.13
    produksi
    -1.13
     keramik
    -1.11
    POSITIVE LOGITS
    }
    1.13
    8
    1.13
    u
    1.13
    9
    1.09
    j
    1.06
     grits
    1.05
    le
    1.05
    다
    1.02
    ara
    1.01
    il
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.