© 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. 16340
    Prev
    Next
    INDEX
    Explanations

    scientific journal abbreviations

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

    academic journal titles and citations.

    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
     sämtliche
    -1.43
    日を
    -1.30
    過程
    -1.24
    時間も
    -1.18
    時間は
    -1.16
    不断的
    -1.15
     keinerlei
    -1.14
    捗
    -1.12
     يمكنك
    -1.09
     dieselben
    -1.07
    POSITIVE LOGITS
    französ
    1.49
    際は
    1.34
    blusa
    1.30
     forskning
    1.24
    música
    1.22
    וּ
    1.21
    ഢ
    1.21
    を超
    1.20
    guitarra
    1.20
     konkrét
    1.19
    Activations Density 0.005%

    No Known Activations