© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12081
    Prev
    Next
    INDEX
    Explanations

    bananas and banishment

    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
     Ajouter
    3.07
    𝐠
    3.02
    لنا
    3.00
    𝐞
    2.99
    𝐭
    2.92
    𝐀
    2.91
    erness
    2.90
    𝐌
    2.89
    elekt
    2.85
    𝐎
    2.83
    POSITIVE LOGITS
    ্দ
    3.49
    ش
    3.17
    ali
    3.08
    রকম
    3.04
    ্দ্র
    2.97
    其
    2.96
     във
    2.89
     تعدى
    2.86
    ная
    2.85
    джа
    2.85
    Activations Density 0.030%

    No Known Activations