© 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. 30825
    Prev
    Next
    INDEX
    Explanations

    main () or code structure

    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
    ȷ
    -0.88
     sogni
    -0.82
     trône
    -0.82
    voices
    -0.80
     rayures
    -0.78
     maintien
    -0.77
    ORNING
    -0.77
    ੂ
    -0.77
    Personas
    -0.76
     légiti
    -0.75
    POSITIVE LOGITS
    putchar
    1.10
     put
    0.85
    PUT
    0.84
     Spanish
    0.82
    iol
    0.82
    ദ്
    0.82
    戟
    0.81
    <<<<<<<
    0.81
    picasso
    0.80
    ATO
    0.77
    Activations Density 0.004%

    No Known Activations