© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36708
    Prev
    Next
    INDEX
    Explanations

    only, unless, not

    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
    cault
    -0.94
    latego
    -0.91
     olarak
    -0.90
    """)
    -0.89
    vikle
    -0.89
    ී
    -0.88
    діть
    -0.88
     articol
    -0.88
     अच्छ
    -0.86
     Приступљено
    -0.86
    POSITIVE LOGITS
     not
    1.07
     or
    0.93
     no
    0.89
     ブック
    0.88
    वान
    0.85
    phal
    0.84
     a
    0.83
     plus
    0.83
     TAMBÉM
    0.83
    )+(
    0.82
    Activations Density 0.192%

    No Known Activations