© 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. 26012
    Prev
    Next
    INDEX
    Explanations

    comparison to others

    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
     навіть
    -1.23
    tiin
    -1.13
    viembre
    -1.09
    なのですが
    -1.07
     fusca
    -1.02
    ());
    -1.02
     nawet
    -1.01
    この
    -1.01
    despite
    -1.01
    valget
    -1.00
    POSITIVE LOGITS
     other
    2.31
     similar
    1.58
    other
    1.56
     others
    1.55
     otras
    1.52
    其他
    1.48
    autres
    1.45
     аналоги
    1.44
     других
    1.40
     innych
    1.38
    Activations Density 0.063%

    No Known Activations