© 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. 93301
    Prev
    Next
    INDEX
    Explanations

    crime Stoppers hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     الشاشة
    -1.14
     καὶ
    -1.02
     Accueil
    -1.01
     اللون
    -1.01
     noël
    -0.99
     banheiro
    -0.98
     réfrig
    -0.98
     ἡ
    -0.95
     atque
    -0.94
     cuillère
    -0.94
    POSITIVE LOGITS
     anonymously
    1.31
     uLocal
    1.21
    ığında
    1.20
     ElevatedButton
    1.16
    шком
    1.15
     reward
    1.14
     affez
    1.14
    anciers
    1.13
     pagare
    1.12
     anonymity
    1.11
    Activations Density 0.003%

    No Known Activations