© 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. 59542
    Prev
    Next
    INDEX
    Explanations

    terrain vehicles Hunt Battlefield

    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
    níci
    -1.42
    keterangan
    -1.30
     môže
    -1.26
    哙
    -1.26
     gezegd
    -1.26
    鬓
    -1.22
     trabajar
    -1.22
     Artículos
    -1.20
    ategy
    -1.18
    Proyectos
    -1.16
    POSITIVE LOGITS
    W
    1.57
    O
    1.49
    \
    1.49
    D
    1.45
     you
    1.34
    V
    1.33
    It
    1.33
    t
    1.32
    E
    1.29
    L
    1.28
    Activations Density 0.044%

    No Known Activations