© 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. 22-GEMMASCOPE-RES-131K
    7. 33842
    Prev
    Next
    INDEX
    Explanations

    survival and energy

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

    technical terms in scientific and technical documents, particularly related to measurements, specifications, and formal descriptions.

    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_22/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
     ogrodow
    -1.13
    ₫
    -1.13
     Wählen
    -1.08
     gikk
    -1.05
     Hawaii
    -1.04
     kutoka
    -1.03
     خالی
    -1.02
     Venise
    -1.01
    还需要
    -1.01
     incomplète
    -1.01
    POSITIVE LOGITS
     and
    1.67
    <bos>
    1.27
    ようと
    1.20
     onCreateView
    1.17
    뭘
    1.15
    옳
    0.99
    ׂ
    0.97
     ExecuteAsync
    0.96
    ってこと
    0.96
    もや
    0.96
    Activations Density 0.049%

    No Known Activations