© 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. 57384
    Prev
    Next
    INDEX
    Explanations

    for this

    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
     botines
    -1.36
     tirantes
    -1.19
     tiroirs
    -1.16
     sandalias
    -1.13
    ätze
    -1.10
     ganchillo
    -1.07
     amikor
    -1.06
    fasterxml
    -1.06
     comodidades
    -1.05
    りましたが
    -1.05
    POSITIVE LOGITS
     to
    5.00
    为此
    2.94
    そのため
    2.42
     To
    2.22
     accomplish
    2.16
    To
    2.16
     accomplishing
    2.11
     bunun
    2.03
     dafür
    1.98
     that
    1.90
    Activations Density 0.231%

    No Known Activations