© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95556
    Prev
    Next
    INDEX
    Explanations

    regional access, local coverage, vascularized, extracellular

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

    code blocks and programming syntax elements.

    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
    They
    -1.29
    <bos>
    -1.18
     they
    -1.15
    ～～～
    -1.10
    などを
    -1.10
    などが
    -1.06
    その
    -1.03
     случаи
    -1.02
    beforeAll
    -1.01
     thus
    -1.00
    POSITIVE LOGITS
     and
    1.13
    mación
    1.06
    
    1.05
    ところに
    1.03
    ことも
    1.02
    様な
    1.01
     dividida
    1.01
     produite
    1.00
    人文
    1.00
    靫
    0.99
    Activations Density 0.000%

    No Known Activations