© 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. 34-GEMMASCOPE-RES-131K
    7. 80854
    Prev
    Next
    INDEX
    Explanations

    less than or equal to comparison

    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_34/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
     <=
    -1.80
     >=
    -1.73
    >=
    -1.60
    ]>=
    -1.59
    ]<=
    -1.51
    <=
    -1.48
    )>=
    -1.46
     ≤
    -1.45
    ≥
    -1.37
    )<=
    -1.35
    POSITIVE LOGITS
     <
    1.62
     >
    1.40
     $<$
    1.39
     < 
    1.24
    }<
    1.23
     more
    1.23
    <
    1.20
     less
    1.18
     smaller
    1.08
     меньше
    1.07
    Activations Density 0.045%

    No Known Activations