© 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. 76545
    Prev
    Next
    INDEX
    Explanations

    Time and location

    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
    apartamento
    -0.74
     shapes
    -0.73
    getStart
    -0.68
     Shapes
    -0.67
     dims
    -0.66
     doel
    -0.66
     Роман
    -0.66
     Drayton
    -0.65
    accus
    -0.65
    アプリ
    -0.64
    POSITIVE LOGITS
    sonic
    0.82
    Denied
    0.80
    derived
    0.74
     Reid
    0.74
    Sonic
    0.73
    Reid
    0.71
     imported
    0.71
     Sonic
    0.71
    pied
    0.67
    enix
    0.66
    Activations Density 0.057%

    No Known Activations