© 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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 611
    Prev
    Next
    INDEX
    Explanations

    quantities, large numbers, units

    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_16k_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
    AL
    1.69
    a
    1.59
     maquin
    1.49
    ilizar
    1.49
    of
    1.47
     σειρά
    1.46
    NIE
    1.43
    dairy
    1.42
     retardation
    1.42
     insanity
    1.41
    POSITIVE LOGITS
     millones
    1.61
     mètres
    1.59
    ة
    1.49
     человек
    1.48
     ribu
    1.47
    м
    1.42
    \%)
    1.39
    %%\
    1.36
    р
    1.34
    TypeValue
    1.34
    Activations Density 1.144%

    No Known Activations