© 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. 87390
    Prev
    Next
    INDEX
    Explanations

    asking what does it

    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
    2
    -3.03
    7
    -2.53
    6
    -2.52
    5
    -2.50
    4
    -2.44
    8
    -2.38
    0
    -2.31
     avec
    -2.20
    3
    -2.19
    9
    -2.16
    POSITIVE LOGITS
     which
    2.14
     usually
    2.02
     distribuidor
    2.02
    قرير
    2.02
     started
    2.00
    咐
    2.00
     subtly
    1.97
     стран
    1.96
     occasionally
    1.93
     הם
    1.90
    Activations Density 0.013%

    No Known Activations