© 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. 129132
    Prev
    Next
    INDEX
    Explanations

    YapMurmur,buff,log,Methyl

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

    computer programming and technical code-related terms.

    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
     desfile
    -1.23
    米国
    -1.16
    Numerous
    -1.15
     when
    -1.11
    weitere
    -1.10
    꾀
    -1.10
     Warszawie
    -1.10
    Ecotoxicity
    -1.10
    when
    -1.09
    WHEN
    -1.09
    POSITIVE LOGITS
     like
    1.20
     каждого
    1.16
     our
    1.13
     gevonden
    1.11
    提升
    1.11
    alisco
    1.08
     vuitton
    1.07
    ulso
    1.07
     here
    1.06
    ler
    1.05
    Activations Density 0.069%

    No Known Activations