© 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. 70567
    Prev
    Next
    INDEX
    Explanations

    in this regard

    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
     with
    -1.55
     viejas
    -1.54
     deciso
    -1.48
    蛧
    -1.45
     from
    -1.42
     for
    -1.41
     purposes
    -1.38
     resulted
    -1.38
    ństw
    -1.33
     messed
    -1.32
    POSITIVE LOGITS
    \
    1.63
     they
    1.36
     souvent
    1.29
    (!__
    1.28
    )\}$
    1.26
    箪
    1.26
    恐怕
    1.24
     oraz
    1.24
     каждого
    1.23
    ‚¬
    1.23
    Activations Density 0.031%

    No Known Activations