© 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
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 293
    Prev
    Next
    INDEX
    Explanations

    unless, because, anymore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    そして
    0.61
     そして
    0.48
    và
    0.47
     و
    0.47
    MLLoader
    0.46
    と共に
    0.43
     तथा
    0.43
     ۽
    0.43
    그리고
    0.42
    ździer
    0.42
    POSITIVE LOGITS
     unless
    1.12
    unless
    0.95
     anymore
    0.93
     Unless
    0.90
     because
    0.86
     إلا
    0.84
     क्योंकि
    0.82
    除非
    0.81
     karena
    0.79
    ទេ។
    0.77
    Activations Density 0.052%

    No Known Activations