© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101360
    Prev
    Next
    INDEX
    Explanations

    differential diagnosis of seizures or Brent crude

    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
    AdvEx
    -1.70
    rrrrr
    -1.68
    rrrr
    -1.59
    ctory
    -1.47
     will
    -1.43
    rrrrrrrr
    -1.42
    gggg
    -1.39
    〮
    -1.37
     more
    -1.36
    更多
    -1.34
    POSITIVE LOGITS
    埸
    1.52
    侷
    1.44
    尷
    1.40
    躋
    1.38
    ↵
    1.31
    鷽
    1.31
    傢
    1.30
    予算
    1.27
    慫
    1.27
    .”.
    1.26
    Activations Density 0.238%

    No Known Activations