© 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. 83047
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
    ++$
    -1.07
    zake
    -0.91
     vivre
    -0.88
    avin
    -0.88
     lancé
    -0.88
     Abp
    -0.86
    :+:
    -0.85
    метра
    -0.85
    {}
    -0.84
    émy
    -0.84
    POSITIVE LOGITS
     =
    3.27
    =
    2.17
     $=
    2.11
    }}=
    2.05
    }=
    1.99
     $=\
    1.94
    >=</
    1.87
     = 
    1.80
    }=\
    1.80
    $=
    1.73
    Activations Density 0.016%

    No Known Activations