© 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. 34-GEMMASCOPE-RES-131K
    7. 106949
    Prev
    Next
    INDEX
    Explanations

    code definitions and includes

    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_34/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
    わけではない
    -0.84
     Alemanha
    -0.82
     myocardial
    -0.81
     winter
    -0.76
    resser
    -0.75
    reibung
    -0.75
    écu
    -0.74
     destinée
    -0.73
    iit
    -0.73
     Suède
    -0.72
    POSITIVE LOGITS
    define
    0.99
    if
    0.93
     define
    0.84
     Также
    0.84
     esiste
    0.82
    nity
    0.79
     pliable
    0.77
     romeo
    0.77
     définir
    0.75
    ธิ
    0.75
    Activations Density 0.030%

    No Known Activations