© 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. 22279
    Prev
    Next
    INDEX
    Explanations

    chemical compound names containing acid

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

    chemical terms containing the word "acid" in scientific or technical contexts.

    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
    I
    -3.09
    丏
    -2.64
    缐
    -2.58
    嵓
    -2.39
    (
    -2.39
     deine
    -2.38
    The
    -2.34
    臯
    -2.30
    だけど
    -2.23
    苼
    -2.22
    POSITIVE LOGITS
     две
    2.39
     amplificador
    2.19
     vollständ
    2.16
    unjungi
    2.16
     \&
    2.16
    ที่
    2.13
     ausdrück
    2.11
     problemlos
    2.08
     verwendeten
    2.08
     vorliegenden
    2.06
    Activations Density 0.019%

    No Known Activations