© 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. 59650
    Prev
    Next
    INDEX
    Explanations

    dialkylaminoalkyl ethers

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

    chemical compounds and terms related to amines in organic chemistry.

    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
    </em>
    -1.84
    l
    -1.73
    ti
    -1.70
    …”
    -1.67
    ……
    -1.67
    ese
    -1.65
    ….
    -1.65
    on
    -1.63
     {
    -1.59
    A
    -1.55
    POSITIVE LOGITS
    螄
    1.57
    StreetMap
    1.54
     Xperia
    1.53
    Недостатки
    1.52
    IZIONE
    1.50
    dibujos
    1.45
    ถ้า
    1.44
    ervazione
    1.40
    mejores
    1.40
    אם
    1.40
    Activations Density 0.206%

    No Known Activations