© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130819
    Prev
    Next
    INDEX
    Explanations

    charitable donations and support

    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
    waits
    -1.21
     but
    -1.21
     only
    -1.05
    vaila
    -1.04
    Ré
    -1.03
    ceptable
    -1.02
    tempt
    -0.97
    madeus
    -0.95
     possibilities
    -0.95
     acceptable
    -0.95
    POSITIVE LOGITS
     donated
    1.27
     karyawan
    1.23
     employees
    1.20
     donate
    1.17
     compassion
    1.17
     compassionate
    1.16
     employee
    1.16
     help
    1.11
     gesture
    1.09
     donations
    1.09
    Activations Density 0.060%

    No Known Activations