© 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. 10-GEMMASCOPE-RES-131K
    7. 60368
    Prev
    Next
    INDEX
    Explanations

    achieving states or goals

    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_10/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
    了
    -1.26
     zuerst
    -1.23
     určit
    -1.19
    On
    -1.18
    While
    -1.17
    veux
    -1.17
    But
    -1.16
     recently
    -1.14
    Recently
    -1.14
    Both
    -1.13
    POSITIVE LOGITS
     muun
    1.28
    ismer
    1.23
    -¡
    1.16
    cress
    1.15
    tigung
    1.14
    gmail
    1.14
    badan
    1.13
     anul
    1.13
    følge
    1.12
    groupBox
    1.11
    Activations Density 0.150%

    No Known Activations