© 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. 10-GEMMASCOPE-RES-131K
    7. 40084
    Prev
    Next
    INDEX
    Explanations

    military staff and strategy

    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
     captiv
    -1.38
     våre
    -1.17
     our
    -1.17
    满脸
    -1.16
     steeply
    -1.16
    いき
    -1.16
    瑧
    -1.15
     encomp
    -1.14
     nossas
    -1.14
     autres
    -1.13
    POSITIVE LOGITS
     where
    1.59
     not
    1.34
     like
    1.33
     oplossing
    1.26
    splan
    1.26
     selben
    1.26
    losseum
    1.20
    mantec
    1.18
    irement
    1.18
     superiori
    1.17
    Activations Density 0.036%

    No Known Activations