© 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. 682
    Prev
    Next
    INDEX
    Explanations

    throughout the day or year

    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
    मेट्री
    0.67
    gekehrt
    0.67
    Re
    0.62
    غا
    0.62
    چین
    0.61
     появление
    0.60
    ोजा
    0.59
     Ö
    0.58
     chwil
    0.58
     ló
    0.58
    POSITIVE LOGITS
     journée
    0.92
     daily
    0.89
     dagen
    0.89
     giornata
    0.80
     throughout
    0.80
     the
    0.79
     året
    0.77
     dnev
    0.77
    Daily
    0.77
     anului
    0.77
    Activations Density 0.051%

    No Known Activations