© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33851
    Prev
    Next
    INDEX
    Explanations

    Ava, Eva, and Lava names

    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
     constituents
    -0.76
    स
    -0.75
     kurze
    -0.74
    Angleterre
    -0.73
    ls
    -0.73
     distributions
    -0.72
     particolarmente
    -0.71
    borne
    -0.70
    営業時間
    -0.70
     personagens
    -0.68
    POSITIVE LOGITS
    LLLL
    0.93
    洸
    0.88
    GGGG
    0.78
    eren
    0.76
    дження
    0.75
    ilets
    0.75
    apol
    0.75
    EMAN
    0.75
    rative
    0.74
    技
    0.74
    Activations Density 0.026%

    No Known Activations