© 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. 45691
    Prev
    Next
    INDEX
    Explanations

    terms of use and 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
     seguenti
    -0.76
    jahteraan
    -0.74
    oltán
    -0.73
     Hæ
    -0.71
    zucker
    -0.69
     Linger
    -0.68
    ciated
    -0.68
    給
    -0.68
    chés
    -0.68
     statuses
    -0.68
    POSITIVE LOGITS
     Terms
    3.48
     terms
    3.42
    Terms
    3.25
    terms
    2.91
     TERMS
    2.39
    TERMS
    2.39
     agreement
    2.34
     agree
    2.11
     agreements
    2.05
    agreement
    2.02
    Activations Density 0.094%

    No Known Activations