© 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. 34-GEMMASCOPE-RES-131K
    4. 81073
    Prev
    Next
    INDEX
    Explanations

    conversation and discussion

    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_34/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
     for
    -1.07
     statement
    -0.94
    的故事
    -0.93
    statement
    -0.93
     story
    -0.89
     STATEMENT
    -0.87
     çalış
    -0.86
     announce
    -0.85
     resp
    -0.85
     explained
    -0.85
    POSITIVE LOGITS
     about
    1.85
     conducted
    1.41
    关于
    1.37
     حول
    1.34
    conducted
    1.30
     regarding
    1.25
     discussing
    1.23
     Conducted
    1.20
     overheard
    1.19
     между
    1.18
    Activations Density 0.040%

    No Known Activations