© 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. 47883
    Prev
    Next
    INDEX
    Explanations

    book preface or volume

    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
     highlighted
    -1.06
     like
    -1.05
     and
    -0.99
     focusing
    -0.98
     Steven
    -0.98
    what
    -0.98
     Steve
    -0.98
     starts
    -0.96
    iencing
    -0.95
    Steve
    -0.95
    POSITIVE LOGITS
     vocales
    1.14
    ̓
    1.06
     ridiculous
    1.05
     ridiculously
    1.04
    Digitized
    1.04
    ⁠
    1.01
     THEIR
    0.97
     ?)
    0.94
    לום
    0.94
    InstanceId
    0.92
    Activations Density 0.014%

    No Known Activations