© 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. 34-GEMMASCOPE-RES-131K
    7. 86827
    Prev
    Next
    INDEX
    Explanations

    assembly metadata and code

    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
     joint
    -0.68
    seed
    -0.62
    崛起
    -0.62
    Defines
    -0.62
     Seeds
    -0.61
    anggil
    -0.60
     klingt
    -0.60
    Joint
    -0.59
    Advantages
    -0.59
     Joint
    -0.59
    POSITIVE LOGITS
    vocable
    0.71
     thong
    0.69
    ッフ
    0.68
     ustaw
    0.68
    rida
    0.66
    herd
    0.65
    TTS
    0.65
    ři
    0.64
    IZI
    0.64
     موج
    0.63
    Activations Density 0.074%

    No Known Activations