© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 67219
    Prev
    Next
    INDEX
    Explanations

    new growth, integration

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

    cryptocurrency manipulation and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    س
    0.49
    सव
    0.46
    า
    0.45
    descricao
    0.44
    宾
    0.44
    watermelon
    0.43
     Bingo
    0.42
    हू
    0.42
    anych
    0.42
    َّا
    0.41
    POSITIVE LOGITS
    成長
    0.49
     integration
    0.44
    ដោយ
    0.44
     increment
    0.44
     grafted
    0.44
     modification
    0.43
     слабо
    0.43
     intrav
    0.43
     transnational
    0.43
    境外
    0.42
    Activations Density 0.003%

    No Known Activations