© 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. 65819
    Prev
    Next
    INDEX
    Explanations

    Garland, Randolph, Starr names

    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
    .”
    -2.39
    埸
    -2.36
    二百
    -2.33
     tisíc
    -2.31
     escuchadas
    -2.31
     puntas
    -2.27
    磧
    -2.27
    Ꝑ
    -2.22
     незавер
    -2.20
    $-$\\
    -2.20
    POSITIVE LOGITS
     
    3.17
    铊
    2.66
    some
    2.55
    媗
    2.48
    ཥ
    2.42
    ︲
    2.39
    聼
    2.39
    𖧵
    2.36
    that
    2.36
     espet
    2.34
    Activations Density 0.007%

    No Known Activations