© 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. 30585
    Prev
    Next
    INDEX
    Explanations

    living people

    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
    Iter
    -0.87
    Experimental
    -0.82
    aser
    -0.78
    gebob
    -0.77
    iter
    -0.76
    iziert
    -0.73
     downloaded
    -0.73
    ITER
    -0.71
     ממש
    -0.71
     causando
    -0.71
    POSITIVE LOGITS
     оси
    0.69
    Agencia
    0.68
    longitud
    0.68
    Gravel
    0.68
     Gravel
    0.68
    Agua
    0.65
     apostles
    0.64
    moor
    0.63
     nervioso
    0.63
     sticks
    0.62
    Activations Density 0.051%

    No Known Activations