© 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. 73508
    Prev
    Next
    INDEX
    Explanations

    program license text

    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
    FieldSet
    -0.66
    աց
    -0.65
    흘
    -0.65
    createTable
    -0.63
     Première
    -0.63
    öße
    -0.62
    TTT
    -0.62
    Démographie
    -0.61
     Biennial
    -0.61
    DIRS
    -0.60
    POSITIVE LOGITS
    Dissertation
    0.75
    資
    0.72
    тного
    0.71
    に関
    0.68
    vač
    0.67
     برانيه
    0.66
     electing
    0.65
    勾
    0.65
    ∠
    0.65
    𝕥
    0.65
    Activations Density 0.065%

    No Known Activations