© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95376
    Prev
    Next
    INDEX
    Explanations

    financial transactions and accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    苯
    -1.26
    localScale
    -1.09
    ׇ
    -1.08
    Goed
    -1.05
     géographie
    -1.04
     podemos
    -1.03
    尤其
    -1.02
    pão
    -1.01
     aporte
    -1.00
     особенно
    -0.99
    POSITIVE LOGITS
    PUESTA
    1.34
    bundet
    1.23
    に行ってきました
    1.19
     acogedor
    1.19
    钞
    1.18
    :"-
    1.17
    ᾿
    1.16
    volent
    1.14
    𝐱
    1.13
    電腦
    1.12
    Activations Density 0.026%

    No Known Activations