© 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. 22-GEMMASCOPE-2-RES-262K
    7. 2675
    Prev
    Next
    INDEX
    Explanations

    their eyes; there are; here is

    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_22_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
     them
    0.91
    them
    0.80
     ihnen
    0.76
     ماما
    0.75
     Them
    0.73
    ၎င်း
    0.71
    وہ
    0.69
    鄔
    0.69
    覦
    0.68
    மொழ
    0.68
    POSITIVE LOGITS
    зовы
    0.79
    attacking
    0.77
    includes
    0.75
    ყ
    0.74
    atever
    0.74
    क्‍त
    0.73
    ᇁ
    0.73
    FORE
    0.73
     desg
    0.72
     બાળકો
    0.72
    Activations Density 0.000%

    No Known Activations