© 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. 22-GEMMASCOPE-RES-131K
    7. 34288
    Prev
    Next
    INDEX
    Explanations

    trip advisor

    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_22/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
     大きい
    -2.38
     incluidas
    -2.34
     were
    -2.28
    鈊
    -2.25
     possibility
    -2.19
    苼
    -2.17
     哪些
    -2.14
    ⽩
    -2.13
    ']
    -2.08
    ⁛
    -2.05
    POSITIVE LOGITS
     was
    2.69
    i
    2.69
     Its
    2.52
     Of
    2.42
    section
    2.27
     They
    2.22
     Mitarbeitern
    2.14
    if
    2.14
     факты
    2.13
    鼉
    2.08
    Activations Density 0.008%

    No Known Activations