© 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. 34-GEMMASCOPE-RES-131K
    4. 102735
    Prev
    Next
    INDEX
    Explanations

    business and financial reporting

    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_34/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
     whopping
    -1.23
     that
    -1.13
    ここ
    -1.12
     nötig
    -1.09
    人们
    -1.09
    แค่
    -1.04
    解决
    -1.02
    这
    -1.02
     viszont
    -1.02
    この
    -1.01
    POSITIVE LOGITS
     }^{(
    1.32
     pursuant
    1.26
     Company
    1.23
    ּוֹ
    1.23
     Messrs
    1.20
     approximately
    1.16
     materially
    1.13
     отметить
    1.13
    fastjson
    1.12
    idän
    1.12
    Activations Density 0.099%

    No Known Activations