© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 108241
    Prev
    Next
    INDEX
    Explanations

    arachnoid cysts

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

    proper names of places or institutions with unique spelling patterns.

    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
     and
    -2.36
    __(
    -1.37
    strator
    -1.36
     %),
    -1.35
    /}
    -1.34
    を行い
    -1.34
    に行った
    -1.32
    に行く
    -1.31
    様が
    -1.30
    “,
    -1.29
    POSITIVE LOGITS
    を使って
    1.42
    もありますが
    1.30
     データ
    1.30
     contextLoads
    1.27
     diferite
    1.26
     使い方
    1.25
    但是在
    1.24
    では
    1.24
     リスト
    1.24
     変更
    1.23
    Activations Density 0.412%

    No Known Activations