© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12374
    Prev
    Next
    INDEX
    Explanations

    awaiting asynchronous tasks

    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
     will
    -1.38
    Each
    -1.27
     is
    -1.27
     Gruß
    -1.25
     Große
    -1.25
    fillText
    -1.24
     могли
    -1.20
    &
    -1.17
    DESCRIPCIÓN
    -1.16
    攫
    -1.16
    POSITIVE LOGITS
     vitamine
    1.23
    素晴らしい
    1.18
    grains
    1.15
    
    1.12
     говорил
    1.09
    excellents
    1.09
     государства
    1.07
    铡
    1.06
    )+"
    1.06
    planet
    1.05
    Activations Density 0.001%

    No Known Activations