© 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. 10-GEMMASCOPE-RES-131K
    7. 1797
    Prev
    Next
    INDEX
    Explanations

    binary states or choices

    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_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
     and
    -1.38
     što
    -1.21
    atórios
    -1.16
     և
    -1.16
     második
    -1.14
    ,
    -1.10
     面
    -1.09
     \&
    -1.09
    wheres
    -1.09
     کمک
    -1.08
    POSITIVE LOGITS
     this
    1.59
     there
    1.56
     now
    1.48
     these
    1.45
    Colore
    1.34
     armament
    1.22
    Manufact
    1.20
    ناول
    1.18
     вдруг
    1.17
     obiettivi
    1.17
    Activations Density 0.119%

    No Known Activations