© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112471
    Prev
    Next
    INDEX
    Explanations

    topical drug and skin applications

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

    topical medical treatments and medications.

    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
    了一口
    -1.24
     Anzahl
    -1.22
    ahh
    -1.21
    हन
    -1.17
     into
    -1.14
    ::::::::::::::::
    -1.07
     
    -1.05
     Advantages
    -1.04
     Contracts
    -1.03
    <h2>
    -1.02
    POSITIVE LOGITS
    when
    1.44
     thrilling
    1.25
    vės
    1.24
    Remember
    1.23
    ὲν
    1.23
    </h3>
    1.22
     sprawling
    1.22
     Parenthood
    1.22
     коды
    1.22
    PutPixel
    1.21
    Activations Density 0.242%

    No Known Activations