© 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. 55979
    Prev
    Next
    INDEX
    Explanations

    property assignments

    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
     pensamento
    -0.96
    appears
    -0.96
    想过
    -0.94
     แต่
    -0.92
     龙
    -0.92
    袛
    -0.91
     []
    -0.90
     [],
    -0.89
     domínio
    -0.89
    戋
    -0.88
    POSITIVE LOGITS
     =
    1.86
    =
    1.30
    }}=
    1.19
    >=</
    1.00
     }}=\
    1.00
    ']=$
    0.99
    VEC
    0.98
    Perché
    0.97
     Mischung
    0.96
     $=$
    0.95
    Activations Density 0.028%

    No Known Activations