© 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. 90867
    Prev
    Next
    INDEX
    Explanations

    code comments or licenses

    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
     фильма
    -0.68
    ORNING
    -0.67
     gamer
    -0.66
    ὁ
    -0.66
    arten
    -0.66
     crescendo
    -0.64
    ClientID
    -0.64
    artner
    -0.64
     sehari
    -0.63
     zip
    -0.63
    POSITIVE LOGITS
    ussis
    0.70
    readable
    0.68
    useppe
    0.64
     verfügb
    0.63
    可用
    0.63
     живут
    0.62
    releases
    0.60
     зре
    0.60
     Loeb
    0.59
     encara
    0.59
    Activations Density 0.076%

    No Known Activations