© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58576
    Prev
    Next
    INDEX
    Explanations

    degradation or degraded

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

    instances where quality or performance is declining or deteriorating.

    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_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
    ⎆
    -2.92
    驺
    -2.53
    廰
    -2.42
    谂
    -2.23
     ส์
    -2.19
    轳
    -2.19
    
    -2.14
    鋱
    -2.11
    ᭝
    -2.09
    ᆞ
    -2.08
    POSITIVE LOGITS
    ↵
    3.28
     of
    2.73
    ’
    2.42
     
    2.38
    ]
    2.31
    [
    2.28
    {
    2.14
     .
    2.09
    (
    1.97
     on
    1.91
    Activations Density 0.014%

    No Known Activations