© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 754
    Prev
    Next
    INDEX
    Explanations

    presence of absence

    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
     still
    -1.65
     العالمي
    -1.28
     between
    -1.25
    ऎ
    -1.25
     around
    -1.18
     into
    -1.17
    abond
    -1.16
     zunächst
    -1.15
     time
    -1.12
     还
    -1.11
    POSITIVE LOGITS
    1.42
    而不是
    1.34
    
    1.24
    ématiques
    1.23
    Permalink
    1.21
                               
    1.16
    (()
    1.15
    tually
    1.13
    
    1.11
    hooter
    1.10
    Activations Density 0.068%

    No Known Activations