© 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. 12468
    Prev
    Next
    INDEX
    Explanations

    define problems or needs

    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
    Their
    -1.66
    despite
    -1.56
    anyone
    -1.48
    basically
    -1.47
    ఝ
    -1.46
    amazing
    -1.45
    Might
    -1.40
    currently
    -1.39
    seems
    -1.39
     leurs
    -1.38
    POSITIVE LOGITS
     your
    2.53
     that
    2.17
     what
    2.13
     where
    2.06
     there
    1.92
     it
    1.91
     if
    1.84
     before
    1.81
     about
    1.80
     which
    1.68
    Activations Density 0.063%

    No Known Activations