© 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. 23716
    Prev
    Next
    INDEX
    Explanations

    free space or calcium

    np_acts-logits-general · gemini-2.5-flash-lite

    references to memory, disk space, or storage capacity in computing contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ⓗ
    -0.74
     energética
    -0.71
     încă
    -0.71
    колай
    -0.70
    linky
    -0.69
    рила
    -0.69
    长的
    -0.68
    блон
    -0.67
    ALTY
    -0.66
     Perspek
    -0.66
    POSITIVE LOGITS
     free
    4.44
    free
    3.75
    Free
    3.27
     Free
    3.17
     свобод
    2.83
    FREE
    2.80
     FREE
    2.67
     свобо
    2.36
     available
    2.20
     آزاد
    2.16
    Activations Density 0.085%

    No Known Activations