© 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. 68362
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and attributes

    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
     not
    -1.37
     their
    -1.30
     it
    -1.29
     there
    -1.27
    ."
    -1.21
    で一番
    -1.21
     körül
    -1.16
    ",
    -1.15
    の結果
    -1.13
     ΤΟ
    -1.11
    POSITIVE LOGITS
    がありますが
    1.59
    鐽
    1.31
    があるので
    1.30
    Continu
    1.25
    があります
    1.23
    Vendo
    1.23
    などが
    1.20
    しかし
    1.20
     может
    1.20
    了一眼
    1.20
    Activations Density 0.001%

    No Known Activations