© 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. 66037
    Prev
    Next
    INDEX
    Explanations

    chapter headings or titles

    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
     another
    -1.18
     again
    -1.03
     same
    -0.94
     second
    -0.93
     these
    -0.91
     Another
    -0.91
     updated
    -0.88
     latest
    -0.88
     even
    -0.87
     gainera
    -0.84
    POSITIVE LOGITS
     Rebirth
    0.92
     Onions
    0.90
    acas
    0.89
     Altri
    0.88
    )))
    0.88
     Concer
    0.88
    mockMvc
    0.87
    🍤
    0.86
     Reservation
    0.86
     Justi
    0.84
    Activations Density 0.047%

    No Known Activations