© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118094
    Prev
    Next
    INDEX
    Explanations

    Vla, Vladimir, VLC, Ł

    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
    żym
    -0.82
    illah
    -0.82
    леге
    -0.74
    ⠘
    -0.72
     Massacre
    -0.71
    濺
    -0.70
     』
    -0.69
    Camping
    -0.69
     Kristin
    -0.69
    Marion
    -0.68
    POSITIVE LOGITS
    ęku
    0.81
    мых
    0.78
     sofá
    0.75
     houver
    0.74
    amir
    0.74
     uncut
    0.73
     Urteil
    0.73
     spit
    0.73
     odd
    0.72
    Spit
    0.71
    Activations Density 0.015%

    No Known Activations