© 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. 34-GEMMASCOPE-RES-131K
    7. 57260
    Prev
    Next
    INDEX
    Explanations

    word pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    つまり
    -1.22
    ఱ
    -1.17
    鑷
    -1.10
    ਖ਼
    -1.09
    ってみました
    -1.04
    꿨
    -1.02
    これらの
    -1.02
    偶尔
    -1.00
    ̖
    -0.96
     kolejne
    -0.96
    POSITIVE LOGITS
    thodox
    1.22
    ?=
    1.13
    😞
    1.13
    😕
    1.12
    🤠
    1.10
    thodoxy
    1.09
    strator
    1.07
     indien
    1.07
    😪
    1.05
    🤨
    1.05
    Activations Density 0.138%

    No Known Activations