© 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. 30394
    Prev
    Next
    INDEX
    Explanations

    Taylor & Francis

    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
    ⌨
    -0.87
    lação
    -0.85
    風の
    -0.83
     navideñas
    -0.82
     аксе
    -0.81
     both
    -0.81
    ladu
    -0.81
    லி
    -0.81
    Phaser
    -0.79
     között
    -0.78
    POSITIVE LOGITS
     stattfinden
    0.93
     NACA
    0.83
     vrea
    0.80
     subsequ
    0.79
     autrement
    0.77
     abenço
    0.76
     geprü
    0.76
     intermitt
    0.74
    indicated
    0.73
    今度
    0.73
    Activations Density 0.003%

    No Known Activations