© 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. 22-GEMMASCOPE-RES-131K
    7. 12160
    Prev
    Next
    INDEX
    Explanations

    court, circuit, or root

    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
    膏
    -1.00
    timos
    -0.99
     вони
    -0.97
     tirs
    -0.96
     <<<<<<<<<<<<<<
    -0.92
     potrebbero
    -0.92
     brune
    -0.92
     sembl
    -0.91
     rocher
    -0.90
    Aquila
    -0.89
    POSITIVE LOGITS
     or
    1.62
     anywhere
    1.28
    either
    1.26
     будь
    1.16
     either
    1.09
     any
    1.06
    וּ
    1.03
     статистика
    1.00
    Any
    0.99
     including
    0.98
    Activations Density 0.089%

    No Known Activations