© 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. 8428
    Prev
    Next
    INDEX
    Explanations

    Generated programming, medical, and scientific terms

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

    Java annotations in programming code, particularly @GeneratedValue.

    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
    or
    -2.83
    1
    -2.50
     {
    -2.36
    -2.25
    leq
    -2.25
    er
    -2.22
    cdot
    -2.19
    rightarrow
    -2.17
     be
    -2.16
    I
    -2.16
    POSITIVE LOGITS
    getBytes
    2.84
    疍
    2.38
    嫱
    2.36
    灩
    2.36
     syarat
    2.30
    icksburg
    2.22
    
    2.17
    还有什么
    2.16
    ﻏ
    2.14
     メニュー
    2.13
    Activations Density 0.000%
    No Known Activations