© 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. 10-GEMMASCOPE-RES-131K
    7. 19574
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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_10/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
     Also
    -1.75
     from
    -1.73
    Also
    -1.65
     your
    -1.48
    ꪻ
    -1.43
     on
    -1.39
    거나
    -1.37
    ᠌
    -1.37
     Basically
    -1.36
     Usually
    -1.35
    POSITIVE LOGITS
     is
    1.86
     to
    1.70
    好好的
    1.25
    -
    1.24
     другую
    1.20
    cessed
    1.19
    joyed
    1.16
     durante
    1.13
    ीत
    1.13
     mediante
    1.13
    Activations Density 0.629%

    No Known Activations