© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11833
    Prev
    Next
    INDEX
    Explanations

    states of completion or resolution

    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
     špec
    -1.49
     símbolos
    -1.34
     is
    -1.34
     típicos
    -1.28
     últimos
    -1.28
     nouvelles
    -1.20
     pourraient
    -1.20
    ↵↵
    -1.18
     nieuwe
    -1.16
     auront
    -1.16
    POSITIVE LOGITS
     that
    1.57
    Since
    1.46
    Nearly
    1.42
    Before
    1.37
    Without
    1.34
    Now
    1.33
    Almost
    1.28
    Regardless
    1.27
    Once
    1.27
     almost
    1.27
    Activations Density 0.102%

    No Known Activations