© 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. 67410
    Prev
    Next
    INDEX
    Explanations

    bitter, bittersweet

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

    words or phrases relating to bitterness, particularly the adjective "bitter" or words with the root "bitter" in them.

    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
     a
    -2.16
    你来
    -1.96
     were
    -1.82
     anchored
    -1.72
     absoluta
    -1.70
     surges
    -1.66
    翻訳
    -1.66
    你会
    -1.65
     aspiring
    -1.65
     geared
    -1.65
    POSITIVE LOGITS
    mathrm
    2.19
     tinham
    2.08
    ↵
    2.00
    та
    1.92
    3
    1.91
     RSITY
    1.83
    有何
    1.74
    纡
    1.72
    where
    1.71
    0
    1.66
    Activations Density 0.009%

    No Known Activations