© 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. 11978
    Prev
    Next
    INDEX
    Explanations

    right side

    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
    țiilor
    2.17
    ל
    2.16
    čių
    2.15
     respet
    2.10
    չ
    2.03
    tcpHeader
    2.03
     мл
    2.01
    ১২
    2.00
    లపై
    1.99
     mettre
    1.97
    POSITIVE LOGITS
    daki
    2.54
    most
    2.21
    gramModel
    2.12
    halb
    2.11
    på
    2.06
     kiu
    2.06
    categorie
    2.05
     percentile
    2.05
    
    2.05
    此同时
    2.04
    Activations Density 0.042%

    No Known Activations