© 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. 10-GEMMASCOPE-RES-131K
    7. 71838
    Prev
    Next
    INDEX
    Explanations

    isoforms, listOf

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

    functions or methods that operate on collections, particularly "listOf" and related identifiers for working with data structures.

    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_10/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
    ’
    -2.45
    หรือ
    -2.41
     is
    -2.27
     juſ
    -2.25
    0
    -2.20
    га
    -2.20
    zelfde
    -2.17
    л
    -2.17
    </strong>
    -2.09
     пять
    -2.09
    POSITIVE LOGITS
    s
    3.22
    喾
    3.17
    垍
    3.11
     美食
    2.42
    This
    2.36
    UCIÓN
    2.34
    𖣘
    2.33
     If
    2.30
     memili
    2.23
     腳
    2.20
    Activations Density 0.001%

    No Known Activations