© 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. 10-GEMMASCOPE-RES-131K
    7. 110545
    Prev
    Next
    INDEX
    Explanations

    want to / need to

    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_10/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
    -1.47
     other
    -1.43
     maar
    -1.42
    “
    -1.36
     qual
    -1.36
     only
    -1.34
     can
    -1.34
     would
    -1.25
    _
    -1.24
    )$.
    -1.22
    POSITIVE LOGITS
     también
    1.91
     также
    1.83
     همچنین
    1.67
     également
    1.59
    Also
    1.59
     også
    1.59
     também
    1.48
     كذلك
    1.47
    また
    1.46
     also
    1.45
    Activations Density 0.093%

    No Known Activations