© 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. 22-GEMMASCOPE-RES-131K
    4. 130698
    Prev
    Next
    INDEX
    Explanations

    technical compound words

    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
     whom
    -0.94
     Männern
    -0.94
    krish
    -0.92
     including
    -0.92
    鸚
    -0.92
     names
    -0.90
     túl
    -0.89
    毅
    -0.89
    ственных
    -0.89
     those
    -0.89
    POSITIVE LOGITS
     klaus
    1.13
     valle
    1.07
     gada
    1.02
     lü
    1.01
    】:
    0.99
    freundlich
    0.98
     marta
    0.97
     "))
    0.97
     vanden
    0.96
     icke
    0.96
    Activations Density 0.069%

    No Known Activations