© 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. 22-GEMMASCOPE-RES-131K
    7. 27667
    Prev
    Next
    INDEX
    Explanations

    current and recent status

    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
     pluralism
    -1.16
     penurunan
    -1.16
    ESD
    -1.16
     meest
    -1.12
     our
    -1.10
    祢
    -1.09
    捫
    -1.09
    AIRE
    -1.09
    FEST
    -1.08
    ='';
    -1.07
    POSITIVE LOGITS
     since
    1.70
     currently
    1.68
    tualmente
    1.63
     recently
    1.62
     has
    1.56
    felizmente
    1.48
     actualmente
    1.47
     Actualmente
    1.47
    Recently
    1.46
    Currently
    1.37
    Activations Density 0.066%

    No Known Activations