© 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. 72867
    Prev
    Next
    INDEX
    Explanations

    Chromosome breakage

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

    web API paths and documentation hierarchies.

    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
    Agar
    -1.03
    therners
    -1.00
    ‏
    -0.86
    ziesz
    -0.85
     milhões
    -0.84
    lokasi
    -0.84
     plaît
    -0.83
    ....
    -0.83
    лася
    -0.83
    ......
    -0.82
    POSITIVE LOGITS
    ฏิ
    1.16
     trám
    1.16
    Díky
    1.13
    嗫
    1.11
    vierno
    1.11
     menyadari
    1.09
     κάνει
    1.07
    similar
    1.07
     spus
    1.04
    ейчас
    1.03
    Activations Density 0.003%

    No Known Activations