© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30278
    Prev
    Next
    INDEX
    Explanations

    input channel or dimension

    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
    rache
    -0.76
     mysterious
    -0.69
     研究
    -0.66
    神秘
    -0.66
    jabi
    -0.65
     söz
    -0.65
    omis
    -0.65
    副本
    -0.65
     Haring
    -0.65
    decorate
    -0.63
    POSITIVE LOGITS
     channel
    1.37
     channels
    1.34
    channel
    1.34
    channels
    1.32
     Channels
    1.30
     height
    1.20
     Height
    1.20
    Channels
    1.16
     Channel
    1.13
    height
    1.07
    Activations Density 0.015%

    No Known Activations