© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59581
    Prev
    Next
    INDEX
    Explanations

    code structure components

    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
     hermosas
    -1.24
    つも
    -1.14
     cadeaux
    -1.13
    みたいに
    -1.12
     autén
    -1.11
    ったり
    -1.11
     amables
    -1.09
    往前
    -1.09
    oczes
    -1.09
     choses
    -1.09
    POSITIVE LOGITS
     if
    2.25
     now
    2.16
     for
    1.88
     only
    1.65
     first
    1.58
     here
    1.56
     since
    1.49
     and
    1.46
     we
    1.44
     если
    1.37
    Activations Density 0.025%

    No Known Activations