© 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. 128325
    Prev
    Next
    INDEX
    Explanations

    leach, leaching, leech

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

    words and phrases related to "leaching" or liquid extraction processes.

    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
    ઁ
    -2.34
    𓐍
    -2.34
    ꜆
    -2.31
    盌
    -2.20
     categorized
    -2.13
    ſa
    -2.13
     embarc
    -2.09
    媄
    -2.08
     ส์
    -2.08
    けれ
    -2.05
    POSITIVE LOGITS
     básicamente
    2.75
     anoche
    2.58
     téc
    2.44
     "
    2.39
    DbHelper
    2.25
     allí
    2.25
     aslında
    2.14
    𞤢
    2.14
     TAMBIÉN
    2.13
     I
    2.11
    Activations Density 0.003%

    No Known Activations