© 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. 9087
    Prev
    Next
    INDEX
    Explanations

    as you

    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
    й
    1.08
    us
    1.03
    ので
    1.03
    ag
    0.94
    ab
    0.89
    ર
    0.87
    é
    0.81
    𝑠
    0.81
    j
    0.79
    at
    0.76
    POSITIVE LOGITS
     evidenced
    1.02
    仅
    0.91
     отметить
    0.87
    ૂર્વ
    0.83
     rửa
    0.81
    ের
    0.80
    ⚙
    0.79
    ٺ
    0.77
    enio
    0.77
     quenched
    0.77
    Activations Density 0.215%

    No Known Activations