© 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. 32812
    Prev
    Next
    INDEX
    Explanations

    keywords followed by variable names

    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
    uccess
    -1.07
    potentially
    -1.05
    lana
    -1.03
    larg
    -1.01
     acht
    -1.01
     kamera
    -1.01
    quite
    -1.01
    ఙ
    -0.98
     annen
    -0.98
     lange
    -0.96
    POSITIVE LOGITS
     сделать
    0.96
     for
    0.95
     on
    0.90
     According
    0.90
    !!!!
    0.90
     as
    0.87
    !!!!!
    0.87
    馳走
    0.86
     because
    0.86
     doing
    0.85
    Activations Density 0.027%

    No Known Activations