© 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. 68460
    Prev
    Next
    INDEX
    Explanations

    programming and technical documentation

    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
    You
    -1.04
    веси
    -1.02
     even
    -0.99
     nasional
    -0.98
     banjir
    -0.97
     tipe
    -0.95
     беже
    -0.93
     portatil
    -0.91
    Even
    -0.91
    These
    -0.91
    POSITIVE LOGITS
     streamlining
    1.02
    ఱ
    0.99
    edere
    0.98
     [],
    0.96
    PONENTS
    0.94
     lavoratori
    0.94
    ridescent
    0.94
     rác
    0.94
    lieve
    0.93
    nade
    0.93
    Activations Density 0.001%

    No Known Activations