© 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. 101665
    Prev
    Next
    INDEX
    Explanations

    plaintiffs and respondents

    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
     those
    -1.89
     "'");
    -1.51
     coloridas
    -1.48
     sentado
    -1.45
     senere
    -1.43
     asegurarse
    -1.43
     delicado
    -1.42
     mogelijkheid
    -1.41
     sólido
    -1.38
     also
    -1.38
    POSITIVE LOGITS
     diferite
    1.62
    different
    1.47
     diferentes
    1.45
     were
    1.37
     différentes
    1.37
    må
    1.31
    b
    1.29
    k
    1.29
    avao
    1.29
    has
    1.27
    Activations Density 0.030%

    No Known Activations