© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49084
    Prev
    Next
    INDEX
    Explanations

    looks like / approximate descriptors

    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_34/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
    nski
    -0.80
     extenso
    -0.79
    tigung
    -0.79
     様
    -0.78
    alez
    -0.77
     eindeutig
    -0.76
    はじめに
    -0.74
     identical
    -0.74
    cvs
    -0.73
     ſi
    -0.73
    POSITIVE LOGITS
     approximate
    5.38
     approximately
    4.59
    Approximate
    4.53
     roughly
    4.53
    approximate
    4.31
     Approximate
    4.16
     примерно
    3.97
    approximately
    3.95
    approx
    3.88
    roughly
    3.86
    Activations Density 0.219%

    No Known Activations