© 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. 49275
    Prev
    Next
    INDEX
    Explanations

    md5 and sha checksums

    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
    WARDS
    -0.82
    xspace
    -0.72
    teli
    -0.70
    析
    -0.70
    coba
    -0.70
     پاس
    -0.69
    AAF
    -0.68
    小程序
    -0.68
     Sato
    -0.68
    است
    -0.68
    POSITIVE LOGITS
     MD
    4.50
     md
    4.16
    MD
    4.03
    md
    3.86
    Md
    3.27
     Md
    3.09
     SHA
    3.06
    SHA
    3.02
    sha
    2.75
     sha
    2.67
    Activations Density 0.149%

    No Known Activations