© 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
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8824
    Prev
    Next
    INDEX
    Explanations

    rationality, choice, logic, and mathematics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dst
    3.17
    Survived
    2.98
    ра
    2.93
    iness
    2.85
    𝓷
    2.70
     noqa
    2.68
    𝙍
    2.67
    roles
    2.63
     vacated
    2.59
    দারি
    2.58
    POSITIVE LOGITS
    ة
    3.32
    ק
    2.82
    ب
    2.81
    ్వ
    2.77
    лдуу
    2.77
    如图
    2.73
    нің
    2.57
    י
    2.54
    phabet
    2.49
    ك
    2.46
    Activations Density 0.042%

    No Known Activations