© 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. 70687
    Prev
    Next
    INDEX
    Explanations

    mutual funds and investment management

    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
     again
    -1.23
    מעות
    -1.02
    further
    -1.00
    Inhalts
    -0.99
    我去
    -0.99
     further
    -0.97
    __,
    -0.94
    リーツ
    -0.93
     ഒരു
    -0.93
    ğmen
    -0.91
    POSITIVE LOGITS
    ׂ
    1.60
    ּוֹ
    1.54
    ִּ
    1.51
    turma
    1.38
    ְּ
    1.34
    האם
    1.30
    boston
    1.29
    nosť
    1.23
     мнению
    1.20
    וּ
    1.19
    Activations Density 0.026%

    No Known Activations